Volkan Cevher
+41 21 693 11 01
EPFL
>
STI
>
STI-SEL
>
SEL-ENS
EPFL STI IEL LIONS
ELE 233 (Bâtiment ELE)
Station 11
1015 Lausanne
+41 21 693 11 01
+41 21 693 11 74
Office:
ELE 233
EPFL
>
STI
>
IEM
>
LIONS
Web site: Web site: https://lions.epfl.ch
+41 21 693 11 01
EPFL
>
P
>
P-EM
>
CCE
Web site: Web site: https://cce.epfl.ch/
+41 21 693 11 01
EPFL
>
P
>
P-EM
>
AE
Web site: Web site: https://ae.epfl.ch/
Web site: Web site: https://epflch.sharepoint.com/sites/CDS
Fields of expertise
Machine Learning
Optimization
Reinforcement Learning
Deep learning
Optimization
Reinforcement Learning
Deep learning
Biography
Volkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park, from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. He was also a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University from 2010-2020. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and an Amazon Scholar. His research interests include machine learning, optimization theory and methods, and automated control. Dr. Cevher is an IEEE Fellow ('24), an ELLIS fellow, and was the recipient of the ICML AdvML Best Paper Award in 2023, Google Faculty Research award in 2018, the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.Publications
Infoscience publications
Selected Publications
Adaptive Bilevel Optimization
ACM / IMS Journal of Data Science. 2025. DOI : 10.1145/3728478.Addressing Label Shift In Distributed Learning Via Entropy Regularization
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Faster Inference Of Flow-Based Generative Models Via Improved Data-Noise Coupling
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Efficient Interpolation Between Extragradient And Proximal Methods For Weak MVIS
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Adversarial Training For Defense Against Label Poisoning Attacks
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Quantum-Peft: Ultra Parameter-Efficient Fine-Tuning
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Certified Robustness Under Bounded Levenshtein Distance
2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.Hadamard product in deep learning: Introduction, Advances and Challenges
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025. DOI : 10.1109/TPAMI.2025.3560423.Membership Inference Attacks against Large Vision-Language Models
2024. 38th Annual Conference on Neural Information Processing Systems, Vancouver Convention Center, 2024-12-10 - 2024-12-15.SAMPa: Sharpness-aware Minimization Parallelized
38th Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2024-12-10 - 2024-12-15.REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-07-21.Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-07-21.Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks
Journal of Machine Learning Research. 2024.Truly No-Regret Learning in Constrained MDPs
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-07-21. p. 36605 - 36653.Mixed Nash for Robust Federated Learning
Transactions on Machine Learning Research. 2024.Universal Gradient Methods for Stochastic Convex Optimization
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-07-21.Imitation Learning in Discounted Linear MDPs without exploration assumptions
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.Graph generative deep learning models with an application to circuit topologies
Lausanne, EPFL, 2024. DOI : 10.5075/epfl-thesis-9020.Robust NAS under adversarial training: benchmark, theory, and beyond
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.Efficient Continual Finite-Sum Minimization
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.Multilinear Operator Networks
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 2024-05-07 - 2024-05-11.On the Generalization of Stochastic Gradient Descent with Momentum
Journal Of Machine Learning Research. 2024.Improving SAM Requires Rethinking its Optimization Formulation
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.Revisiting Character-level Adversarial Attacks for Language Models
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.Learning to Remove Cuts in Integer Linear Programming
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.Generalization of Scaled Deep ResNets in the Mean-Field Regime
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.Efficient local linearity regularization to overcome catastrophic overfitting
2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.Stable Nonconvex-Nonconcave Training via Linear Interpolation
2023. Thirty-seventh Conference on Neural Information Processing Systems, New Orleans, Louisiana, USA, December 10-16, 2023.A unified stochastic approximation framework for learning in games
Mathematical Programming. 2023. DOI : 10.1007/s10107-023-02001-y.Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees
2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.Maximum Independent Set: Self-Training through Dynamic Programming
2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023)., New Orlean, USA, December 10-16. 2023.Finding Actual Descent Directions For Adversarial Training
2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
2023. 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, December 10-16. 2023.On the Convergence of Encoder-only Shallow Transformers
2023. 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, December 10-16. 2023.Efficient Online Clustering with Moving Costs
2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orlean, USA, December 10-16. 2023.Alternation makes the adversary weaker in two-player games
2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orlean, USA, December 10-16. 2023.Regularization of polynomial networks for image recognition
2023. Computer Vision and Pattern Recognition Conference (CVPR), Vancouver, Canada, 18-22 June, 2023.Adversarial Training Should Be Cast As a Non-Zero-Sum Game
2023Robust Training and Verification of Deep Neural Networks
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-9223.Federated Learning under Covariate Shifts with Generalization Guarantees
Transactions on Machine Learning Research. 2023.When do Minimax-fair Learning and Empirical Risk Minimization Coincide?
2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July 23-29, 2023.Solving stochastic weak Minty variational inequalities without increasing batch size
11th International Conference on Learning Representations ICLR2023, Kigali, Rwanda, May 1-5, 2023.Revisiting adversarial training for the worst-performing class
Transactions on Machine Learning Research. 2023.Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling
2023. 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, December 10-16. 2023.What can online reinforcement learning with function approximation benefitfrom general coverage conditions
2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.Augmented Lagrangian Methods for Provable and Scalable Machine Learning
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-9613.DiGress: Discrete Denoising diffusion for graph generation
2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.Benign Overfitting in Deep Neural Networks under Lazy Training
2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.Universal and adaptive methods for robust stochastic optimization
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-9077.Regularization of polynomial networks for image recognition
2023. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, CANADA, JUN 17-24, 2023. p. 16123 - 16132. DOI : 10.1109/CVPR52729.2023.01547.Improving Generalization of Pretrained Language Models
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-8664.Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.Sound and Complete Verification of Polynomial Networks
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 - December 3, 2022.Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 - December 3, 2022.A Natural Actor-Critic Framework for Zero-Sum Markov Games
2022. 39th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.Predicting in Uncertain Environments: Methods for Robust Machine Learning
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-9118.Extra Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees
2022. 39th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.On The Convergence Of Stochastic Primal-Dual Hybrid Gradient
Siam Journal On Optimization. 2022. DOI : 10.1137/19M1296252.The spectral bias of polynomial neural networks
2022. 10th International Conference on Learning Representations (ICLR), Virtual, April 25-29, 2022.Learning to sample in Cartesian MRI
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-9981.High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize
2022. 10th International Conference on Learning Representations (ICLR), Virtual, April 25-29, 2022.A 16-Channel Neural Recording System-on-Chip With CHT Feature Extraction Processor in 65-nm CMOS
IEEE Journal of Solid-State Circuits. 2022. DOI : 10.1109/JSSC.2022.3161296.Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization
2022. 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022), [ Virtual only] Valencia, Spain, March 28-30, 2022.Controlling the Complexity and Lipschitz Constant improves Polynomial Nets
2022. 10th International Conference on Learning Representations (ICLR), Virtual, April 25-29, 2022.Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration
2022. Thirty-sixth Conference on Neural Information Processing Systems - NeurIPS 2022, New Orleans, USA, November 28 - December 3, 2022.On the Double Descent of Random Features Models Trained with SGD
2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, USA, November 28 - December 3, 2022.Proximal Point Imitation Learning
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 - December 3, 2022.Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models
2022. 38th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
2022. 10th International Conference on Learning Representations (ICLR 2022), Virtual, April 25-29, 2022.Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 - December 3, 2022.Generalization Properties of NAS under Activation and Skip Connection Search
2022. 36th Conference on Neural Information Processing Systems - NeurIPS 2022, New Orleans, USA, November 28 - December 3, 2022.Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
2022. 36th Conference on Neural Information Processing Systems - NeurIPS 2022, New Orleans, USA, November 28 - December 3, 2022.No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation
2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, USA, November 28 - December 9, 2022.A Newton Frank-Wolfe method for constrained self-concordant minimization
Journal Of Global Optimization. 2022. DOI : 10.1007/s10898-021-01105-z.Forward-reflected-backward method with variance reduction
Computational Optimization and Applications. 2021. DOI : 10.1007/s10589-021-00305-3.A 16-Channel Wireless Neural Recording System-on-Chip with CHT Feature Extraction Processor in 65nm CMOS
2021. 2021 IEEE Custom Integrated Circuits Conference (CICC), Virtual, April 25-30, 2021. DOI : 10.1109/CICC51472.2021.9431458.The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
2021. 38th International Conference on Machine Learning (ICML 2021), Online, July 18-24, 2021. p. 4337 - 4348.Convergence of adaptive algorithms for constrained weakly convex optimization
2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.Kernel Conjugate Gradient Methods with Random Projections
Applied and Computational Harmonic Analysis. 2021. DOI : 10.1016/j.acha.2021.05.004.Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond
Lausanne, EPFL, 2021. DOI : 10.5075/epfl-thesis-8120.Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.An Optimal-Storage Approach to Semidefinite Programming Using Approximate Complementarity
Siam Journal On Optimization. 2021. DOI : 10.1137/19M1244603.A first-order primal-dual method with adaptivity to local smoothness
2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.Resource Trade-Offs in Circuits and Systems: from Neurotechnology to Communications
Lausanne, EPFL, 2021. DOI : 10.5075/epfl-thesis-9082.Scalable Semidefinite Programming
SIAM Journal on Mathematics of Data Science. 2021. DOI : 10.1137/19M1305045.A reflected forward-backward splitting method for monotone inclusions involving Lipschitzian operators
Set-valued and Variational analysis. 2021. DOI : 10.1007/s11228-020-00542-4.A Plug-and-Play Deep Image Prior
2021. International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021), Toronto, Canada, June 6-11, 2021. DOI : 10.1109/ICASSP39728.2021.9414879.Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities
2021. NeurIPS 2021 : Thirty-fifth Conference on Neural Information Processing Systems, Sydney, Australia [Virtual only], December 6-14, 2021.Asynchronous sar adc with unit length capacitors and constant common mode monotonic switching
WO2021161163 . 2021.An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation
Information-Theoretic Methods in Data Science; Cambridge University Press, 2021. p. 487 - 528.Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
2021. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
2020An AC-Coupled Wideband Neural Recording Front-End With Sub-1 mm2×fJ/conv-step Efficiency and 0.97 NEF
IEEE Solid-State Circuits Letters. 2020. DOI : 10.1109/LSSC.2020.3013993.Optimization for Reinforcement Learning: From a single agent to cooperative agents
Ieee Signal Processing Magazine. 2020. DOI : 10.1109/MSP.2020.2976000.Machine Learning From Distributed, Streaming Data [From the Guest Editors]
Ieee Signal Processing Magazine. 2020. DOI : 10.1109/MSP.2020.2972654.Lipschitz constant estimation for Neural Networks via sparse polynomial optimization
2020. 8th International Conference on Learning Representations, Addis Ababa, ETHIOPIA, April 26-30, 2020.Double-Loop Unadjusted Langevin Algorithm
2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces
Applied and Computational Harmonic Analysis. 2020. DOI : 10.1016/j.acha.2018.09.009.Conditional gradient methods for stochastically constrained convex minimization
2020. 37th International Conference on Machine Learning (ICML), virtual, July 12-18, 2020.Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
2020. 37th International Conference on Machine Learning (ICML), Virtual, July 13-18, 2020.Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections
Journal of Machine Learning Research. 2020.Convergence without Convexity: Sampling, Optimization, and Games
Lausanne, EPFL, 2020. DOI : 10.5075/epfl-thesis-10349.Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
Journal of Machine Learning Research. 2020.Random extrapolation for primal-dual coordinate descent
2020. 37th International Conference on Machine Learning (ICML 2020), Online, July 13-18, 2020.A new regret analysis for Adam-type algorithms
2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 13-18, 2020.An adaptive primal-dual framework for nonsmooth convex minimization
Mathematical Programming Computation. 2020. DOI : 10.1007/s12532-019-00173-3.Scalable Learning-Based Sampling Optimization For Compressive Dynamic MRI
2020. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 4-8, 2020. p. 8584 - 8588. DOI : 10.1109/ICASSP40776.2020.9053345.Interactive Teaching Algorithms for Inverse Reinforcement Learning
2019. The 28th International Joint Conference on Artificial Intelligence, 2019., Macao, China, August 10-16, 2019.Interactive Teaching Algorithms for Inverse Reinforcement Learning
2019. 28th International Joint Conference on Artificial Intelligence, 2019, Macao, China, August 10-16, 2019. p. 2692 - 2700.Chemical machine learning with kernels: The impact of loss functions
International Journal Of Quantum Chemistry. 2019. DOI : 10.1002/qua.25872.Inertial Three-Operator Splitting Method and Applications
SIAM Conference on Optimization - OP17, Vancouver, British Columbia, Canada, May 22-25, 2017.Ultrasensitive hyperspectral imaging and biodetection enabled by dielectric metasurfaces
Nature Photonics. 2019. DOI : 10.1038/s41566-019-0394-6.Data-driven Measurement Designs for Magnetic Resonance Imaging
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9651.Convergence of the Exponentiated Gradient Method with Armijo Line Search
Journal of Optimization Theory and Applications. 2019. DOI : 10.1007/s10957-018-1428-9.Rethinking Sampling in Parallel MRI: A Data-Driven Approach
2019. 27th European Signal Processing Conference (EUSIPCO), Coruña, Spain, September 2-6, 2019. DOI : 10.23919/EUSIPCO.2019.8903150.On the convergence of stochastic primal-dual hybrid gradient
2019A Conditional Gradient-Based Augmented Lagrangian Framework
2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.Stochastic Frank-Wolfe for Composite Convex Minimization
2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.Scalable Convex Optimization Methods for Semidefinite Programming
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9598.A Learning-Based Framework for Quantized Compressed Sensing
IEEE Signal Processing Letters. 2019. DOI : 10.1109/LSP.2019.2898350.An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.Streaming Low-Rank Matrix Approximation With An Application To Scientific Simulation
SIAM Journal on Scientific Computing. 2019. DOI : 10.1137/18M1201068.Efficient learning of smooth probability functions from Bernoulli tests with guarantees.
2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.Fast and Provable ADMM for Learning with Generative Priors
2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.Iterative Classroom Teaching
2019. 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Hawaii, USA, January 27 – February 1, 2019. p. 5684 - 5692. DOI : 10.1609/aaai.v33i01.33015684.Robust Adaptive Decision Making: Bayesian Optimization and Beyond
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9147.Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator
2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.On Certifying Non-Uniform Bounds against Adversarial Attacks
2019. 36th International Conference on Machine Learning (ICML)'2019, Long Beach, USA, June 9-15, 2019.Overlapping Multi-Bandit Best Arm Identification
2019. The 2019 IEEE International Symposium on Information Theory (ISIT), Paris, France, July 7-12, 2019. p. 2544 - 2548. DOI : 10.1109/ISIT.2019.8849327.Almost surely constrained convex optimization
2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.Near-Optimal Noisy Group Testing via Separate Decoding of Items
IEEE Journal of Selected Topics In Signal Processing. 2018. DOI : 10.1109/JSTSP.2018.2844818.On the linear convergence of the stochastic gradient method with constant step-size
Optimization Letters. 2018. DOI : 10.1007/s11590-018-1331-1.Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
2018A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming
2018. the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.Online Adaptive Methods, Universality and Acceleration
2018. 32nd Conference on Neural Information Processing Systems conference (NIPS 2018), Montreal, Canada, December 3-8, 2018. p. 6500 - 6509.Near-Optimal Noisy Group Testing via Separate Decoding of Items
2018. IEEE International Symposium on Information Theory, Colorado, USA., June 17-22. 2018. p. 2311 - 2315. DOI : 10.1109/ISIT.2018.8437667.Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
2018. 35th International Conference on Machine Learning, Stockholm, Sweden, July 10 -15, 2018.Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
2018. 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization
SIAM Journal on Optimization. 2018. DOI : 10.1137/16M1093094.A single-phase, proximal path-following framework
Mathematics of Operations Research. 2018. DOI : 10.1287/moor.2017.0907.Learning without Smoothness and Strong Convexity
Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8765.Adaptive Learning-Based Compressive Sampling for Low-power Wireless Implants
2018. 1st International Symposium on Integrated Circuits and Systems (ISICAS), Taormina, Italy, September 02-03, 2018. p. 3929 - 3941. DOI : 10.1109/TCSI.2018.2853983.Stochastic Three-Composite Convex Minimization with a Linear Operator
2018. 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarotte, Spain, April 9-11, 2018.An area and power efficient on-the-fly LBCS transformation for implantable neuronal signal acquisition systems
2018. ACM International Conference on Computing Frontiers 2018, Ischia, Italy, May 8-10, 2018. p. 228 - 231. DOI : 10.1145/3203217.3203260.Stochastic Forward-Douglas-Rachford Splitting for Monotone Inclusions
Stochastic Forward Douglas-Rachford Splitting Method for Monotone Inclusions; Springer International Publishing, 2018.Robust Maximization of Non-Submodular Objectives
2018. International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Canary Islands, April, 9-11, 2018.An area and power efficient on-the-fly LBCS transformation for implantable neuronal signal acquisition systems
2018. 15th ACM International Conference on Computing Frontiers, Ischia, ITALY, May 08-10, 2018. p. 228 - 231. DOI : 10.1145/3203217.3203260.Learning-Based Hardware Design for Data Acquisition Systems
Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8693.Adversarially Robust Optimization with Gaussian Processes
2018. Conference on Neural Information Processing Systems (NIPS), Montreal, 2018.Adversarially Robust Optimization with Gaussian Processes
2018. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.Chemical machine learning with kernels: The key impact of loss functions
2018Smoothing Alternating Direction Methods for Fully Nonsmooth Constrained Convex Optimization
Large-Scale and Distributed Optimization; Springer, 2018.Let’s be honest: An optimal no-regret framework for zero-sum games
2018. 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.A Non-Euclidean Gradient Descent Framework for Non-Convex Matrix Factorization
IEEE Transactions on Signal Processing. 2018. DOI : 10.1109/TSP.2018.2870353.Mirrored Langevin Dynamics
2018. Thirty-second Conference on Neural Information Processing Systems (NIPS), Montréal. p. 2878 - 2887.Finding Mixed Nash Equilibria of Generative Adversarial Networks
2018. IEEE International Conference on Machine Learning (ICML)’ 2019, Long Beach, USA, June 9-15, 2019.Learning-Based Compressive MRI
IEEE Transactions On Medical Imaging. 2018. DOI : 10.1109/TMI.2018.2832540.An Eight lanes 7Gb/s/pin Source Synchronous Single-Ended RX with Equalization and Far-End Crosstalk Cancellation for Backplane Channels
IEEE Journal of Solid State Circuits. 2018. DOI : 10.1109/JSSC.2017.2783679.Lower Bounds on Active Learning for Graphical Model Selection
2017. The 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Fort Lauderdale, Florida, USA, April 20-22, 2017.Smoothing technique for nonsmooth composite minimization with linear operator
2017Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
2017. Conference on Neural Information Processing Systems (NIPS), Long Beach.Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
2017. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, December 4-9, 2017.Learning-based subsampling
US10082551 ; US2017109650 . 2017.Combinatorial Penalties: Which structures are preserved by convex relaxations?
2017. 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarotte, Spain, April 9-11, 2017.An Adaptive Sublinear-Time Block Sparse Fourier Transform
2017. ACM Symposium on Theory of Computing (STOC), Montreal, June 19-23, 2017. p. 702 - 715. DOI : 10.1145/3055399.3055462.A Distributed Algorithm for Partitioned Robust Submodular Maximization
2017. IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP). DOI : 10.1109/CAMSAP.2017.8313155.Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage
2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS2017), Fort Lauderdale, Florida, USA, April 20-22, 2017.Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
2017. Conference on Learning Theory (COLT)Conference on Learning Theory (COLT), AmsterdamAmsterdam, Netherlands, July 2017July, 7-10, 2017.Limits on Support Recovery With Probabilistic Models: An Information-Theoretic Framework
IEEE Transactions on Information Theory. 2017. DOI : 10.1109/TIT.2016.2606605.Phase Transitions in the Pooled Data Problem
2017. Conference on Neural Information Processing Systems (NIPS), Long Beach, California, December 2017.Practical Sketching Algorithms For Low-Rank Matrix Approximation
Siam Journal On Matrix Analysis And Applications. 2017. DOI : 10.1137/17M1111590.How little does non-exact recovery help in group testing?
2017. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, March 2017. p. 6090 - 6094. DOI : 10.1109/ICASSP.2017.7953326.Faster Coordinate Descent via Adaptive Importance Sampling
2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, Florida, USA, April 20-22, 2017.General Proximal Gradient Method: A Case for Non-Euclidean Norms
2017.Robust Submodular Maximization: A Non-Uniform Partitioning Approach
2017. The 34th International Conference on Machine Learning (ICML), Sydney, 2017.DCT Learning-Based Hardware Design for Neural Signal Acquisition Systems
2017. Computing Frontiers Conference 2017, Siena, Italy, May 15-17, 2017. p. 391 - 394. DOI : 10.1145/3075564.3078890.Efficient and Near-Optimal Noisy Group Testing: An Information-Theoretic Framework
2017An Efficient Streaming Algorithm for the Submodular Cover Problem
2016. The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS).Converse Bounds for Noisy Group Testing with Arbitrary Measurement Matrices
2016. International Symposium on Information Theory (ISIT), Barcelona, July 10-15, 2016. p. 2868 - 2872. DOI : 10.1109/ISIT.2016.7541823.Learning-Based Compressive Subsampling
IEEE Journal on Selected Topics in Signal Processing. 2016. DOI : 10.1109/Jstsp.2016.2548442.Estimation Error of the Constrained Lasso
2016. 54th Annual Allerton Conf. Communication, Control, and Computing, Monticello, IL, September 27-30, 2016. p. 433 - 438. DOI : 10.1109/ALLERTON.2016.7852263.On the Difficulty of Selecting Ising Models with Approximate Recovery
IEEE Transactions on Signal and Information Processing over Networks. 2016. DOI : 10.1109/Tsipn.2016.2596439.Fixed Points of Generalized Approximate Message Passing with Arbitrary Matrices
2016. IEEE International Symposium on Information Theory, (ISIT), Istanbul, Turkey, July 7-12 2013. p. 7464 - 7474. DOI : 10.1109/ISIT.2013.6620309.Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices
2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9-11, 2016.Learning Data Triage: Linear Decoding Works for Compressive MRI
2016. 41st IEEE International Conference on Acoustics, Speech and Signal Processing. p. 4034 - 4038. DOI : 10.1109/ICASSP.2016.7472435.Partial Recovery Bounds for the Sparse Stochastic Block Model
2016. International Symposium on Information Theory (ISIT), Barcelona, July 10-15, 2016. p. 1904 - 1908. DOI : 10.1109/ISIT.2016.7541630.Stochastic Spectral Descent for Discrete Graphical Models
IEEE Journal of Selected Topics in Signal Processing. 2016. DOI : 10.1109/Jstsp.2015.2505684.Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
2016. Conference on Neural Information Processing Systems (NIPS), Barcelona, December 5-10, 2016.Phase Transitions in Group Testing
2016. ACM-SIAM Symposium on Discrete Algorithms (SODA), Arlington, Virginia, USA, January 10-12, 2016. p. 40 - 53. DOI : 10.1137/1.9781611974331.ch4.Learning-Based Near-Optimal Area-Power Trade-offs in Hardware Design for Neural Signal Acquisition
2016. 26th edition of GLSVLSI, Boston, USA, May 18-20, 2016. p. 433 - 438. DOI : 10.1145/2902961.2903028.Group-Sparse Model Selection: Hardness and Relaxations
IEEE Transactions on Information Theory. 2016. DOI : 10.1109/TIT.2016.2602222.Computational Methods for Underdetermined Convolutive Speech Localization and Separation via Model-based Sparse Component Analysis
Speech Communication. 2016. DOI : 10.1016/j.specom.2015.07.002.Adaptive-Rate Sparse Signal Reconstruction With Application in Compressive Foreground Subtraction
IEEE Transactions on Signal Processing. 2016. DOI : 10.1109/TSP.2016.2544744.Stochastic Three-Composite Convex Minimization
2016. 30th Conference on Neural Information Processing Systems (NIPS2016), Barcelona, Spain, December 5-10, 2016. p. 4329 - 4337.Adaptive-Rate Reconstruction of Time-Varying Signals with Application in Compressive Foreground Extraction
IEEE Transactions on Signal Processing. 2016. DOI : 10.1109/TSP.2016.2544744.Time-Varying Gaussian Process Bandit Optimization
2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9 - 11, 2016.Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization
Ieee Transactions On Signal Processing. 2016. DOI : 10.1109/Tsp.2015.2488598.Randomized Single-View Algorithms for Low-Rank Matrix Approximation
2016Frank-Wolfe Works for Non-Lipschitz Continuous Gradient Objectives: Scalable Poisson Phase Retrieval
2016. 41st IEEE International Conference on Acoustics, Speech and Signal Processing. p. 6230 - 6234. DOI : 10.1109/ICASSP.2016.7472875.Convex block-sparse linear regression with expanders - provably
2016. The 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, May 7-11, 2016. p. 19 - 27.Stochastic Spectral Descent for Restricted Boltzmann Machines
2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, USA, May 9-12, 2015.Composite convex minimization involving self-concordant-like cost functions
2015Dynamic Sparse State Estimation Using ℓ1-ℓ1 Minimization: Adaptive-rate Measurement Bounds, Algorithms and Applications
2015. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015, Brisbane, Queensland, Australia, April 19-24, 2015. p. 3332 - 3336. DOI : 10.1109/ICASSP.2015.7178588.Composite Self-Concordant Minimization
Journal of Machine Learning Research. 2015.A 5.9mW/Gb/s 7Gb/s/pin 8-Lane Single-Ended RX with Crosstalk Cancellation Scheme using a XCTLE and 56-tap XDFE in 32nm SOI CMOS
2015. Symposium on VLSI Circuits, Kyoto, Japan, June 15-19, 2015. p. C228 - C229. DOI : 10.1109/VLSIC.2015.7231267.Sparse Group Covers and Greedy Tree Approximations
2015. 2015 IEEE Internation Symposium on Information Theory, Hong Kong, China, June 14-19, 2015. p. 551 - 555. DOI : 10.1109/ISIT.2015.7282515.Structured Sampling and Recovery of iEEG Signals
2015. IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, Cancun, Mexico, December 13-16, 2015. p. 269 - 272. DOI : 10.1109/CAMSAP.2015.7383788.A totally unimodular view of structured sparsity
2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA, May 9 - 12, 2015.Limits on Support Recovery with Probabilistic Models: An Information-Theoretic Framework
2015. International Symposium on Information Theory, Hong Kong, June 2015. p. 2331 - 2335. DOI : 10.1109/ISIT.2015.7282872.Sparsistency of $\ell_1$-Regularized $M$-Estimators
2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA, May 9-12, 2015.Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost
IEEE Journal of Selected Topics in Signal Processing. 2015. DOI : 10.1109/Jstsp.2015.2400412.A Geometric View on Constrained M-Estimators
2015A Primal-dual Framework For Mixtures Of Regularisers
2015. 23rd European Signal Processing Conference (EUSIPCO 2015), Nice, France, August 31 - September 4 2015. p. 240 - 244. DOI : 10.1109/EUSIPCO.2015.7362381.Scalable Convex Methods for Phase Retrieval
2015. 6th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Cancun, Mexico, December 13-16, 2015. p. 381 - 384. DOI : 10.1109/CAMSAP.2015.7383816.Active Learning of Self-concordant like Multi-index Functions
2015. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015. p. 2189 - 2193. DOI : 10.1109/ICASSP.2015.7178359.Introduction to the Issue on Signal Processing for Big Data
Ieee Journal Of Selected Topics In Signal Processing. 2015. DOI : 10.1109/Jstsp.2015.2418393.What’s the Frequency, Kenneth?: Sublinear Fourier Sampling Off the Grid
Algorithmica. 2015. DOI : 10.1007/s00453-014-9918-0.Consistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression
2015. 40th IEEE Int. Conf. Acoustics, Speech and Signal Processing, Brisbane, Australia, April 19-24, 2015. p. 3606 - 3610. DOI : 10.1109/ICASSP.2015.7178643.A Universal Primal-Dual Convex Optimization Framework
2015. 29th Annual Conference on Neural Information Processing Systems (NIPS2015), Montreal, Canada, December 7-12, 2015.Splitting the Smoothed Primal-Dual Gap: Optimal Alternating Direction Methods
2015Composite convex minimization involving self-concordant-like cost functions
2015. Modelling, Computation and Optimization in Information Systems and Management Sciences (MCO 2015), Metz, France, May 11-13, 2015. p. 155 - 168. DOI : 10.1007/978-3-319-18161-5_14.An optimal first-order primal-dual gap reduction framework for constrained convex optimization
2015Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements
SIAM Journal on Imaging Sciences (SIIMS). 2015. DOI : 10.1137/140998779.WASP: Scalable Bayes via barycenters of subset posteriors
2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, USA, May 9-12, 2015. p. 912 - 920.Preconditioned Spectral Descent for Deep Learning
2015. 29-th Neural Information Processing Systems (NIPS), 2015.Rigorous optimization recipes for sparse and low rank inverse problems with applications in data sciences
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6350.A variational approach to stable principal component pursuit
2014. 30th Conference on Uncertainty in Artificial Intelligence (UAI) 2014, Quebec City, Quebeck, Canada, July 23-27, 2014.Barrier Smoothing for Nonsmooth Convex Minimization
2014. IEEE International Conference on Acoustics, Speech, and Signal Processing, Florence, Italy, May 4-9, 2014. p. 1503 - 1507. DOI : 10.1109/ICASSP.2014.6853848.Bilinear Generalized Approximate Message Passing—Part II: Applications
IEEE Transactions on Signal Processing. 2014. DOI : 10.1109/TSP.2014.2357773.An inexact proximal path-following algorithm for constrained convex minimization
Siam Journal On Optimization. 2014. DOI : 10.1137/130944539.A Primal-Dual Algorithmic Framework for Constrained Convex Minimization
2014Structured Sparsity Models for Reverberant Speech Separation
IEEE Transactions on Audio, Speech and Language Processing. 2014. DOI : 10.1109/Taslp.2013.2297012.Model-based Sketching and Recovery with Expanders
2014. ACM-SIAM Symposium on Discrete Algorithms, Portland, Oregon, USA, January 5-7, 2014. p. 1529 - 1543. DOI : 10.1137/1.9781611973402.112.Metric Learning with Rank and Sparsity Constraints
2014. IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, May 4-9, 2014. p. 21 - 25. DOI : 10.1109/ICASSP.2014.6853550.Convex Optimization for Big Data
IEEE Signal Processing Magazine. 2014. DOI : 10.1109/MSP.2014.2329397.Constrained convex minimization via model-based excessive gap
2014. Advances in Neural Information Processing Systems (NIPS) 2014, Montreal, Quebec, Canada, December 8-11, 2014.Matrix Recipes for Hard Thresholding Methods
Journal Of Mathematical Imaging And Vision. 2014. DOI : 10.1007/s10851-013-0434-7.Time–Data Tradeoffs by Aggressive Smoothing
2014. Conference of Neural Information Processing Systems (NIPS) Foundation 2014, Montreal, Quebec, Canada, December 8-11, 2014.Scalable sparse covariance estimation via self-concordance
2014. Twenty-Eighth AAAI Conference on Artificial Intelligence, Quebec, Canada, July 27-31, 2014. DOI : 10.1609/aaai.v28i1.8960.Bilinear Generalized Approximate Message Passing—Part I: Derivation
IEEE Transactions on Signal Processing. 2014. DOI : 10.1109/TSP.2014.2357776.Model-based Sparse Component Analysis for Reverberant Speech Localization
2014. IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, May 4-9. p. 1439 - 1443. DOI : 10.1109/ICASSP.2014.6853835.MAP Estimation for Bayesian Mixture Models with Submodular Priors
2014. 2014 IEEE International Workshop on Machine Learning for signal processing, Reims, France, Sept 21-24, 2014. DOI : 10.1109/MLSP.2014.6958846.Learning non-parametric basis independent models from point queries via low-rank methods
Applied And Computational Harmonic Analysis. 2014. DOI : 10.1016/j.acha.2014.01.002.Manifold Sparse Beamforming
2013. 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Saint Martin, France, December 15-18, 2013. p. 113 - 116. DOI : 10.1109/CAMSAP.2013.6714020.To Convexify or Not? Regression with Clustering Penalties on Graphs
2013. 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Saint Martin, France, December 15-18. 2013. p. 21 - 24. DOI : 10.1109/CAMSAP.2013.6713997.Randomized Low-Memory Singular Value Projection
2013. 10th International Conference on Sampling Theory and Applications (Sampta), Bremen, Germany, July 1st - July 5th, 2013.Fast Proximal algorithms for Self-concordant function minimization with application to sparse graph selection
2013. 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, May 26-31, 2013. p. 6585 - 6589. DOI : 10.1109/ICASSP.2013.6638935.A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions
2013. 30th International Conference on Machine Learning, Atlanta, GA, USA, June 16-19, 2013. p. 271 - 279.Sparse projections onto the simplex
2013. The 30th International Conference on Machine Learning (ICML) 2013, Atlanta, USA, June 16-21, 2013. p. 280 - 288.Energy-aware adaptive bi-Lipschitz embeddings
2013. 10th International Conference on Sampling Theory and Applications (SampTA), Bremen, Germany, July 1-5, 2013.Convexity in source separation: Models, geometry, and algorithms
IEEE Signal Processing Magazine. 2013. DOI : 10.1109/MSP.2013.2296605.Fast Proximal Algorithms For Self-Concordant Function Minimization With Application To Sparse Graph Selection
2013. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada, May 26-31, 2013. p. 6585 - 6589. DOI : 10.1109/ICASSP.2013.6638935.High-Dimensional Gaussian Process Bandits
2013. Neural Information Processing Systems, Lake Tahoe, Nevada, December 5-8, 2013.Tractability of interpretability via selection of group-sparse models
2013. IEEE International Symposium on Information Theory Proceedings (ISIT), 2013, Istanbul, Turkey, July 7-13, 2013. DOI : 10.1109/ISIT.2013.6620384.Active Learning of Multi-Index Function Models
2012. NIPS (The Neural Information Processing Systems), Lake Tahoe, Reno, Nevada, December 3-8, 2012.Combinatorial Selection and Least Absolute Shrinkage via the CLASH Algorithm
2012. 2012 IEEE International Symposium on Information Theory Proceedings (ISIT), Cambridge, Massachusetts, USA, July 1-6, 2012. p. 2216 - 2220. DOI : 10.1109/ISIT.2012.6283847.Equivalence of synthesis and atomic formulations of sparse recovery
2012. IEEE Statistical Signal Processing Workshop (SSP), Ann Arbor, Michigan, USA, Aug 5-8, 2012. p. 177 - 180. DOI : 10.1109/SSP.2012.6319652.Learning Ridge Functions With Randomized Sampling In High Dimensions
2012. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 25-39, 2012. p. 2025 - 2028. DOI : 10.1109/ICASSP.2012.6288306.Compressible distributions for high-dimensional statistics
IEEE Transactions on Information Theory. 2012. DOI : 10.1109/TIT.2012.2197174.Computational Methods For Structured Sparse Component Analysis of Convolutive Speech Mixtures
2012. The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan, March 25-30, 2012. p. 2425 - 2428. DOI : 10.1109/ICASSP.2012.6288405.Bearing estimation via spatial sparsity using compressive sensing
IEEE Transactions on Aerospace and Electronic Systems. 2012. DOI : 10.1109/TAES.2012.6178067.Hard Thresholding with Norm Constraints
2012. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March, 2012. p. 3645 - 3648. DOI : 10.1109/ICASSP.2012.6288706.Method, apparatus and computer program product for determining the location of a plurality of speech sources
US9689959 ; US2013096922 . 2012.Filtered Variation method for denoising and sparse signal processing
2012. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, Kyoto, Japan, March 25-30, 2012. DOI : 10.1109/ICASSP.2012.6288628.Structured Sparse Coding for Microphone Array Location Calibration
2012. SAPA-SCALE Conference, Portland, Oregon, USA, September 7-13.Matrix ALPS: Accelerated Low Rank and Sparse Matrix Reconstruction
2012. IEEE Statistical Signal Processing Workshop (SSP), Ann Arbor, Michigan, USA, August, 2012. p. 185 - 188. DOI : 10.1109/SSP.2012.6319655.Recipes on Hard Thresholding Methods
2011. 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Puerto Rico, December, 2011. DOI : 10.1109/CAMSAP.2011.6136024.Greedy Dictionary Selection for Sparse Representation
IEEE Journal of Selected Topics in Signal Processing. 2011. DOI : 10.1109/JSTSP.2011.2161862.A Game Theoretic Approach to Expander-based Compressive Sensing
2011. IEEE International Symposium on Information Theory (ISIT), St. Petersburg , Russia, July 31 - August 5, 2011. p. 464 - 468. DOI : 10.1109/ISIT.2011.6034169.Compressive Sensing under Matrix Uncertainties: An Approximate Message Passing Approach
2011. Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, California, USA, November 6-9, 2011. DOI : 10.1109/ACSSC.2011.6190118.Online performance guarantees for sparse recovery
2011. 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011. DOI : 10.1109/ICASSP.2011.5946908.On Accelerated Hard Thresholding Methods for Sparse Approximation
2011. Conference on Wavelets and Sparsity XIV, San Diego, California, USA, Aug 21-24, 2011. DOI : 10.1117/12.894386.Learning Low-Dimensional Signal Models
IEEE Signal Processing Magazine. 2011. DOI : 10.1109/MSP.2010.939733.Compressive sensing meets game theory
2011. 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011. p. 3660 - 3663. DOI : 10.1109/ICASSP.2011.5947144.An Alps View of Sparse Recovery
2011. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011. p. 5808 - 5811. DOI : 10.1109/ICASSP.2011.5947681.Model-Based Compressive Sensing for Multi-Party Distant Speech Recognition
2011. The 36th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011. p. 4600 - 4603. DOI : 10.1109/ICASSP.2011.5947379.Multi-party Speech Recovery Exploiting Structured Sparsity Models
2011. 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 28-31, 2011. p. 185 - 188. DOI : 10.21437/Interspeech.2011-78.Submodular dictionary selection for sparse representation
2010. International Conference on Machine Learning (ICML), Haifa, Israel, June 2010.Sparse Signal Acquisition and Recovery with Graphical Models
IEEE Signal Processing Magazine. 2010. DOI : 10.1109/MSP.2010.938029.Model-based compressive sensing
IEEE Transactions on Information Theory. 2010. DOI : 10.1109/TIT.2010.2040894.Low-dimensional models for dimensionality reduction and signal recovery: A geometric perspective
Proceedings of the IEEE. 2010. DOI : 10.1109/JPROC.2009.2038076.Distributed bearing estimation via matrix completion
2010. 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Dallas, Texas, USA, March 14-19, 2010. DOI : 10.1109/ICASSP.2010.5496281.Fast hard thresholding with Nesterov's gradient method
2010. Advances in Neuronal Information Processing Systems (NIPS) Workshops, Whistler, Canada, December 2010.Model-Based Compressive Sensing for Signal Ensembles
2009. 47th Annual Allerton Conference on Communication, Control and Computing, Monticello, IL, September 2009. p. 244 - 250. DOI : 10.1109/ALLERTON.2009.5394807.Learning with Compressible Priors
2009. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada, December 2009.Recovery of Compressible Signals in Unions of Subspaces
2009. Conference on Information Sciences and Systems (CISS), Baltimore, MD, Mar 18-20, 2009.Near-Optimal Bayesian Localization via Incoherence and Sparsity
2009. IEEE/ACM Information Processing in Sensor Networks (IPSN), San Francisco, CA, Apr 13-16, 2009. p. 205 - 216.Recovery of clustered sparse signals from compressive measurements
2009. International conference on Sampling Theory and Applications(SAMPTA), Marseille, France, 18-22 May, 2009.Compressive sensing recovery of spike trains using a structured sparsity model
2009. Workshop on Signal Processing with Adaptive Sparse Structured Representations (SPARS), Saint-Malo, France, April 06-09, 2009.Vehicle speed estimation using acoustic wave patterns
IEEE Transactions on Signal Processing. 2009. DOI : 10.1109/TSP.2008.2005750.Acoustic sensor network design for position estimation
ACM Transactions on Sensor Networks. 2009. DOI : 10.1145/1525856.1525859.Sparse signal recovery using Markov random fields
2008. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada, December 8-11, 2008.A compressive beamforming method
2008. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, NV, Mar 30-Apr 04, 2008. p. 2617 - 2620. DOI : 10.1109/ICASSP.2008.4518185.Factorized variational approximations for acoustic multi source localization
2008. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, NV, Mar 30-Apr 04, 2008. p. 2409 - 2412. DOI : 10.1109/ICASSP.2008.4518133.Pareto frontiers of sensor networks for localization
2008. IEEE/ACM Information Processing in Sensor Networks (IPSN), St Louis, MO, Apr 22-24, 2008. p. 27 - 38. DOI : 10.1109/IPSN.2008.8.Compressed Sensing For Multi-View Tracking And 3-D Voxel Reconstruction
2008. IEEE International Conference on Image Processing (ICIP), San Diego, CA, Oct 12-15, 2008. p. 221 - 224. DOI : 10.1109/ICIP.2008.4711731.Compressive Sensing For Sensor Calibration
2008. IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM), Darmstadt, GERMANY, Jul 21-23, 2008. p. 175 - 178. DOI : 10.1109/SAM.2008.4606849.Distributed target localization via spatial sparsity
2008. European Conference on Signal Processing (EUSIPCO), Lausanne, Switzerland, August 25-29, 2008.Compressive Sensing for Background Subtraction
2008. European Conference on Computer Vision (ECCV), Marseille, FRANCE, Oct 12-18, 2008. p. 155 - 168. DOI : 10.1007/978-3-540-88688-4_12.Compressive wireless arrays for bearing estimation
2008. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, NV, Mar 30-Apr 04, 2008. p. 2497 - 2500. DOI : 10.1109/ICASSP.2008.4518155.Target tracking using a joint acoustic video system
IEEE Transactions on Multimedia. 2007. DOI : 10.1109/TMM.2007.893340.Design considerations for a heterogeneous network of bearings-only sensors using sensor management
2007. IEEE Aerospace Conference, Big Sky, MT, Mar 03-10, 2007. DOI : 10.1109/AERO.2007.353080.Joint acoustic-video fingerprinting of vehicles, part I
2007. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Honolulu, HI, Apr 15-20, 2007. p. 745 - 748. DOI : 10.1109/ICASSP.2007.366343.Gaussian approximations for energy-based detection and localization in sensor networks
2007. IEEE Statistical Signal Processing Workshop (SSP), Madison, WI, Aug 26-29, 2007. p. 655 - 659. DOI : 10.1109/SSP.2007.4301340.A Monte-Carlo approach for tracking mobile personnel
2007. IEEE Aerospace Conference, Big Sky, MT, Mar 03-10, 2007. DOI : 10.1109/AERO.2007.353046.Implementation of batch-based particle filters for multi-sensor tracking
2007. IEEE Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), St Thomas, VI, Dec 12-14, 2007. p. 257 - 260. DOI : 10.1109/CAMSAP.2007.4498014.Acoustic multi target tracking using direction-of-arrival batches
IEEE Transactions on Signal Processing. 2007. DOI : 10.1109/TSP.2007.893962.Decentralized State Initialization with Delay Compensation for Multi-modal Sensor Networks
Journal of Vlsi Signal Processing Systems for Signal Image and Video Technology. 2007. DOI : 10.1007/s11265-006-0007-8.Low computation and low latency algorithms for distributed sensor network initialization
Signal, Image and Video Processing. 2007. DOI : 10.1007/s11760-007-0014-7.Joint acoustic-video fingerprinting of vehicles, part II
2007. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Honolulu, HI, Apr 15-20, 2007. p. 749 - 752. DOI : 10.1109/ICASSP.2007.366344.Mixed-mode implementation of particle filters
2007. IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), Victoria, Canada, Aug 22-24, 2007. p. 617 - 620. DOI : 10.1109/PACRIM.2007.4313312.Optimal maneuvering of seismic sensors for localization of subsurface targets
IEEE Transactions on Geoscience and Remote Sensing. 2007. DOI : 10.1109/TGRS.2007.894551.A multi target bearing tracking system using random sampling consensus
2007. IEEE Aerospace Conference, Big Sky, MT, Mar 03-10, 2007. DOI : 10.1109/AERO.2007.353045.Convergence analysis for sequential Monte Carlo receivers in communications applications
2006. IEEE DSPWorkshop, Grand Teton National Park, WY, September, 2006. p. 354 - 359. DOI : 10.1109/DSPWS.2006.265405.A Monte-Carlo method for initializing distributed tracking algorithms
2006. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May, 2006. DOI : 10.1109/ICASSP.2006.1661118.Multi target direction-of-arrival tracking using road priors
2006. IEEE Aerospace Conference, Big Sky, MT, March, 2006. DOI : 10.1109/AERO.2006.1655924.A joint radar-acoustic particle filter tracker with acoustic propagation delay compensation
2006. European Conference on Signal Processing (EUSIPCO), Florence, Italy, September, 2006.Optimal experiments with seismic sensors
2006. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May, 2006. DOI : 10.1109/ICASSP.2006.1661176.On low-power analog implementations of particle filters for target tracking
2006. European Conference on Signal Processing (EUSIPCO), Florence, Italy, September, 2006.Acoustic node calibration using moving sources
IEEE Transactions on Aerospace and Electronic Systems. 2006. DOI : 10.1109/TAES.2006.1642574.A range-only multiple target particle filter tracker
2006. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May, 2006. DOI : 10.1109/ICASSP.2006.1661116.Proposal strategies for joint state-space tracking with particle filters
2005. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, PA, March 18-23, 2005. p. 1081 - 1084. DOI : 10.1109/ICASSP.2005.1415596.Estimating target state distributions in a distributed sensor network using a Monte-Carlo approach
2005. IEEE Workshop on Machine Learning for Signal Processing (MLSP), Mystic, CT, September, 2005. p. 305 - 310. DOI : 10.1109/MLSP.2005.1532919.General direction-of-arrival tracking with acoustic nodes
IEEE Transactions on Signal Processing. 2005. DOI : 10.1109/TSP.2004.838947.An acoustic multiple target tracker
2005. IEEE Statistical Signal Processing Conference (SSP), Bordeaux, France, July, 2005. p. 509 - 514. DOI : 10.1109/SSP.2005.1628648.Vehicle tracking using acoustic and video sensors
2004. Army Science Conference (ASC), Orlando, FL, November, 2004.Acoustic node calibration using helicopter sounds and Monte Carlo markov chain methods
2004. IEEE DSP Workshop, Taos Ski Valley, NM, August, 2004. p. 347 - 351. DOI : 10.1109/DSPWS.2004.1437973.Fast initialization of particle filters using a modified Metropolis-Hastings algorithm: Mode-hungry approach
2004. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, Canada, May, 2004. p. 129 - 132. DOI : 10.1109/ICASSP.2004.1326211.Tracking of multiple wideband targets using passive sensor arrays and particle filters
2002. IEEE DSP Workshop, Callaway Gardens, GA, October, 2002. p. 72 - 77. DOI : 10.1109/DSPWS.2002.1231079.Wavelet packet best basis search using generalized Renyi entropy
2002. IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Canada, 2002. p. 1005 - 1008. DOI : 10.1109/CCECE.2002.1013081.2-D sensor position perturbation analysis: Equivalence to AWGN on array outputs
2002. IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM), Washington DC, August, 2002. p. 219 - 223. DOI : 10.1109/SAM.2002.1191032.Sensor array calibration via tracking with the extended Kalman filter
2001. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Salt Lake City, Utah, USA, May 2001. p. 2817 - 2820. DOI : 10.1109/ICASSP.2001.940232.Teaching & PhD
Teaching
Electrical and Electronics Engineering
PhD Students
Abad Rocamora Elias, Abranches Figueiredo Simoes De Carvalho Pedro, Afzal Arshia, Candogan Leyla Naz, Dadi Leello Tadesse, Janchevski Andrej, Mavrothalassitis Ioannis, Neumann Amira Devika, Pethick Thomas Michaelsen, Puigdemont Plana Pol, Viano Luca, Wu Yongtao, Wu Zhengqing, Xie Wanyun, Zhu Zhenyu,Past EPFL PhD Students
Alacaoglu Ahmet , Aprile Cosimo , Bogunovic Ilija , El Halabi Marwa , Gözcü Baran , Hsieh Ya-Ping , Karimi Mahabadi Rabeeh , Kavis Ali , Krawczuk Igor , Kyrillidis Anastasios , Latorre Gomez Fabian Ricardo , Li Yen-Huan , Rolland Paul Thierry Yves , Sahin Mehmet Fatih , Sanchez Thomas , Uran Arda , Yurtsever Alp ,Courses
Mathematics of data: from theory to computation
This course provides an overview of key advances in continuous optimization and statistical analysis for machine learning. We review recent learning formulations and models as well as their guarantees, describe scalable solution techniques and algorithms, and illustrate the trade-offs involved.
Reinforcement learning
This course describes theory and methods for Reinforcement Learning (RL), which revolves around decision making under uncertainty. The course covers classic algorithms in RL as well as recent algorithms under the lens of contemporary optimization.
Training Large Language Models
This PhD-level course dives deep into the training of Large Language Models (LLMs), focusing on the complementary roles of datasets, pre-training and post training methodologies in shaping model performance and scalability.
Online learning in games
This course provides an overview of recent developments in online learning, game theory, and variational inequalities and their point of intersection with a focus on algorithmic development. The primary approach is to lay out the different problem classes and their associated optimal rates.
EECS Seminar: Advanced Topics in Machine Learning
Students learn about advanced topics in machine learning, artificial intelligence, optimization, and data science. Students also learn to interact with scientific work, analyze and understand strengths and weaknesses of scientific arguments of both theoretical and experimental results.