Volkan Cevher

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

Membership Inference Attacks against Large Vision-Language Models

Zhan Li; Y. Wu; Y. Chen; F. Tonin; E. Abad Rocamora et al.

2024. 38th Annual Conference on Neural Information Processing Systems, Vancouver Convention Center, 2024-12-10 - 2024-12-15.

Volkan Cevher

Associate Professor

Fields of expertise

Biography

Publications

Infoscience publications

Selected Publications

Membership Inference Attacks against Large Vision-Language Models

SAMPa: Sharpness-aware Minimization Parallelized

REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Truly No-Regret Learning in Constrained MDPs

Universal Gradient Methods for Stochastic Convex Optimization

On the Generalization of Stochastic Gradient Descent with Momentum

Revisiting Character-level Adversarial Attacks for Language Models

Improving SAM Requires Rethinking its Optimization Formulation

Robust NAS under adversarial training: benchmark, theory, and beyond

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Efficient local linearity regularization to overcome catastrophic overfitting

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Efficient Continual Finite-Sum Minimization

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Learning to Remove Cuts in Integer Linear Programming

Graph generative deep learning models with an application to circuit topologies

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Maximum Independent Set: Self-Training through Dynamic Programming

Alternation makes the adversary weaker in two-player games

Federated Learning under Covariate Shifts with Generalization Guarantees

Solving stochastic weak Minty variational inequalities without increasing batch size

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

Revisiting adversarial training for the worst-performing class

Finding Actual Descent Directions For Adversarial Training

Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees

Robust Training and Verification of Deep Neural Networks

When do Minimax-fair Learning and Empirical Risk Minimization Coincide?

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Regularization of polynomial networks for image recognition

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

Regularization of polynomial networks for image recognition

Improving Generalization of Pretrained Language Models

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

On the Convergence of Encoder-only Shallow Transformers

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

Universal and adaptive methods for robust stochastic optimization

Benign Overfitting in Deep Neural Networks under Lazy Training

Efficient Online Clustering with Moving Costs

DiGress: Discrete Denoising diffusion for graph generation

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Learning to sample in Cartesian MRI

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

A 16-Channel Neural Recording System-on-Chip With CHT Feature Extraction Processor in 65-nm CMOS

The spectral bias of polynomial neural networks

Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Proximal Point Imitation Learning

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

On the Double Descent of Random Features Models Trained with SGD

UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees

A Natural Actor-Critic Framework for Zero-Sum Markov Games

Sound and Complete Verification of Polynomial Networks

Extra Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods

On The Convergence Of Stochastic Primal-Dual Hybrid Gradient

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

A Newton Frank-Wolfe method for constrained self-concordant minimization

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

Generalization Properties of NAS under Activation and Skip Connection Search

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

Forward-reflected-backward method with variance reduction

A 16-Channel Wireless Neural Recording System-on-Chip with CHT Feature Extraction Processor in 65nm CMOS

A reflected forward-backward splitting method for monotone inclusions involving Lipschitzian operators

Kernel Conjugate Gradient Methods with Random Projections

An Optimal-Storage Approach to Semidefinite Programming Using Approximate Complementarity

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

A first-order primal-dual method with adaptivity to local smoothness

The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets