# Volkan Cevher

#### Associate Professor

volkan.cevher@epfl.ch +41 21 693 11 01 http://lions.epfl.ch

**EPFL STI IEL LIONS **

ELE 233 (Bâtiment ELE)

Station 11

CH-1015 Lausanne

+41 21 693 11 01

+41 21 693 11 74

Office: ELE 233

EPFL
>
STI
>
IEL
>
LIONS

Web site: Web site: https://lions.epfl.ch

### Fields of expertise

Optimization

Signal Processing

Information Theory

### 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. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University. His research interests include machine learning, signal processing theory, optimization theory and methods, and information theory. Dr. Cevher is an ELLIS fellow and was the recipient of the 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

#### Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

2020-11-05#### An AC-Coupled Wideband Neural Recording Front-End With Sub-1 mm2×fJ/conv-step Efficiency and 0.97 NEF

*IEEE Solid-State Circuits Letters*. 2020-08-04. DOI : 10.1109/LSSC.2020.3013993.

#### Machine Learning From Distributed, Streaming Data [From the Guest Editors]

*Ieee Signal Processing Magazine*. 2020-05-01. DOI : 10.1109/MSP.2020.2972654.

#### Optimization for Reinforcement Learning: From a single agent to cooperative agents

*Ieee Signal Processing Magazine*. 2020-05-01. DOI : 10.1109/MSP.2020.2976000.

#### Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

2020-04-26. 8th International Conference on Learning Representations, Addis Ababa, ETHIOPIA, April 26-30, 2020.#### A reflected forward-backward splitting method for monotone inclusions involving Lipschitzian operators

*Set-valued and Variational analysis*. 2020-03-19. DOI : 10.1007/s11228-020-00542-4.

#### 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. Thirty-seventh International Conference on Machine Learning - ICML 2020, Vienna, Austria, July 13-18, 2020.#### 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 12-18, 2020.#### A new regret analysis for Adam-type algorithms

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.#### Double-Loop Unadjusted Langevin Algorithm

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.#### Wasserstein Distributionally Robust Learning

Lausanne, EPFL, 2020. DOI : 10.5075/epfl-thesis-10012.#### 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.#### Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections

*Journal of Machine Learning Research*. 2020.

#### Personalizable intervention systems to promote healthy behavior change

Lausanne, EPFL, 2020. DOI : 10.5075/epfl-thesis-10008.#### Scalable Semidefinite Programming

*SIAM Journal on Mathematics of Data Science (SIMODS)*. 2020.

#### Interactive Teaching Algorithms for Inverse Reinforcement Learning

2019-08-10. The 28th International Joint Conference on Artificial Intelligence, 2019., Macao, China, August 10-16, 2019.#### Interactive Teaching Algorithms for Inverse Reinforcement Learning

2019-08-10. 28th International Joint Conference on Artificial Intelligence, 2019., Macao, China, August 10-16, 2019.#### Chemical machine learning with kernels: The impact of loss functions

*International Journal Of Quantum Chemistry*. 2019-05-05. 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*. 2019-04-01. DOI : 10.1038/s41566-019-0394-6.

#### UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

2019-01-01. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, CANADA, Dec 08-14, 2019.#### On the convergence of stochastic primal-dual hybrid gradient

2019#### An adaptive primal-dual framework for nonsmooth convex minimization

*Mathematical Programming Computation*. 2019. DOI : 10.1007/s12532-019-00173-3.

#### Data-driven Measurement Designs for Magnetic Resonance Imaging

Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9651.#### Streaming Low-Rank Matrix Approximation With An Application To Scientific Simulation

*SIAM Journal on Scientific Computing*. 2019-01-01. DOI : 10.1137/18M1201068.

#### Stochastic Frank-Wolfe for Composite Convex Minimization

2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.#### 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.#### Fast and Provable ADMM for Learning with Generative Priors

2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.#### UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

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.#### On Certifying Non-Uniform Bounds against Adversarial Attacks

2019. 36th International Conference on Machine Learning (ICML)'2019, Long Beach, USA, June 9-15, 2019.#### 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.#### 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.#### A Conditional Gradient-Based Augmented Lagrangian Framework

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.#### Almost surely constrained convex optimization

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.#### Rethinking Sampling in Parallel MRI: A Data-Driven Approach

2019. 27th European Signal Processing Conference (EUSIPCO), Coruña, Spain, September 2-6, 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.#### 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.#### A Learning-Based Framework for Quantized Compressed Sensing

*IEEE Signal Processing Letters*. 2019. DOI : 10.1109/LSP.2019.2898350.

#### Robust Adaptive Decision Making: Bayesian Optimization and Beyond

Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9147.#### An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation

*Information-Theoretic Methods in Data Science*; Cambridge University Press, 2019.

#### Convergence of the Exponentiated Gradient Method with Armijo Line Search

*Journal of Optimization Theory and Applications*. 2018-12-03. DOI : 10.1007/s10957-018-1428-9.

#### A Single-Phase, Proximal Path-Following Framework

*Mathematics Of Operations Research*. 2018-11-01. DOI : 10.1287/moor.2017.0907.

#### Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces

*Applied and Computational Harmonic Analysis*. 2018-10-04. DOI : 10.1016/j.acha.2018.09.009.

#### Near-Optimal Noisy Group Testing via Separate Decoding of Items

*IEEE Journal of Selected Topics In Signal Processing*. 2018-10-01. DOI : 10.1109/JSTSP.2018.2844818.

#### On the linear convergence of the stochastic gradient method with constant step-size

*Optimization Letters*. 2018-09-25. DOI : 10.1007/s11590-018-1331-1.

#### Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms

2018-09-03#### A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

2018-07-11. the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.#### Online Adaptive Methods, Universality and Acceleration

2018-07-04. 32nd Conference on Neural Information Processing Systems conference (NIPS 2018), Montreal, Canada, December 3-8, 2018.#### Near-Optimal Noisy Group Testing via Separate Decoding of Items

2018-06-17. IEEE International Symposium on Information Theory, Colorado, USA., June 17-22. 2018. p. 2311-2315.#### Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

2018-06-08. 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

2018-03-11. 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*. 2018-01-11. DOI : 10.1137/16M1093094.

#### Adversarially Robust Optimization with Gaussian Processes

2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.#### Online Adaptive Methods, Universality and Acceleration

2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.#### Mirrored Langevin Dynamics

2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.#### An area and power efficient on-the-fly LBCS transformation for implantable neuronal signal acquisition systems

2018-01-01. 15th ACM International Conference on Computing Frontiers, Ischia, ITALY, May 08-10, 2018. p. 228-231. DOI : 10.1145/3203217.3203260.#### Smoothing Alternating Direction Methods for Fully Nonsmooth Constrained Convex Optimization

*Large-Scale and Distributed Optimization*; Springer, 2018.

#### Sparse Linear Inversion for Strong Gravitational Lenses Reconstruction, Component Separation from Morphological Component Analysis with Multiple Discrimination Criteria

Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8965.#### Adversarially Robust Optimization with Gaussian Processes

2018. Conference on Neural Information Processing Systems (NIPS), Montreal, 2018.#### Finding Mixed Nash Equilibria of Generative Adversarial Networks

2018. IEEE International Conference on Machine Learning (ICML)’ 2019, Long Beach, USA, June 9-15, 2019.#### Real-time DCT Learning-based Reconstruction of Neural Signals

2018. 26th European Signal Processing Conference (EUSIPCO 2018), Rome, Italy, September 3-7. 2018. DOI : 10.23919/EUSIPCO.2018.8553402.#### 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.#### 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.#### Learning-Based Hardware Design for Data Acquisition Systems

Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8693.#### Learning without Smoothness and Strong Convexity

Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8765.#### Learning with Structured Sparsity: From Discrete to Convex and Back.

EPFL, 2018. DOI : 10.5075/epfl-thesis-8516.#### Learning-Based Compressive MRI

*IEEE Transactions On Medical Imaging*. 2018. DOI : 10.1109/TMI.2018.2832540.

#### Mirrored Langevin Dynamics

2018. Thirty-second Conference on Neural Information Processing Systems (NIPS), Montréal.#### Dimension-free Information Concentration via Exp-Concavity

2018. Algorithmic Learning Theory (ALT) 2018, Lanzarote, Spain, April 7-9, 2018.#### Robust Maximization of Non-Submodular Objectives

2018. International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Canary Islands, April, 9-11, 2018.#### High Dimensional Bayesian Optimization via Additive Models with Overlapping Groups

2018. AISTATS, Lanzarote, Spain, April, 9-11, 2018.#### 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.#### 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.#### Chemical machine learning with kernels: The key impact of loss functions

2018#### 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.

#### A Non-Euclidean Gradient Descent Framework for Non-Convex Matrix Factorization

*IEEE Transactions on Signal Processing*. 2018. DOI : 10.1109/TSP.2018.2870353.

#### Stochastic Forward-Douglas-Rachford Splitting for Monotone Inclusions

*Stochastic Forward Douglas-Rachford Splitting Method for Monotone Inclusions*; Springer International Publishing, 2018.

#### Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data

2017-12-04. 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, California, USA, December 4-9, 2017.#### Practical Sketching Algorithms For Low-Rank Matrix Approximation

*Siam Journal On Matrix Analysis And Applications*. 2017. DOI : 10.1137/17M1111590.

#### Streaming 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.#### A Distributed Algorithm for Partitioned Robust Submodular Maximization

2017. IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).#### Phase Transitions in the Pooled Data Problem

2017. Conference on Neural Information Processing Systems (NIPS), Long Beach, California, December 2017.#### Efficient and Near-Optimal Noisy Group Testing: An Information-Theoretic Framework

*IEEE Journal of Selected Topics in Signal Processing*. 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.#### General Proximal Gradient Method: A Case for Non-Euclidean Norms

2017.#### Smoothing technique for nonsmooth composite minimization with linear operator

*Preprint*. 2017.

#### Robust Submodular Maximization: A Non-Uniform Partitioning Approach

2017. The 34th International Conference on Machine Learning (ICML), Sydney, 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.#### 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.#### Learning-based subsampling

US10082551 ; US2017109650 . 2017.#### An Adaptive Sublinear-Time Block Sparse Fourier Transform

2017. ACM Symposium on Theory of Computing (STOC), Montreal, June 19-23, 2017.#### 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.#### 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.#### 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.#### A single-phase, proximal path-following framework

*Mathematics of Operations Research*. 2017.

### Teaching & PhD

#### Teaching

Electrical and Electronics Engineering