 |
Research Interests:
|
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 (most recent)
On the Role of Batch Size in Stochastic Conditional Gradient Methods
2026. 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, 2026-07-06 – 2026-07-11.Multi-agent imitation learning with function approximation: Linear Markov games and beyond
2026. 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, 2026-07-06 – 2026-07-11.Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers
2026. 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, 2026-07-06 – 2026-07-11.Training Neural Networks at Any Scale: An exposition
IEEE Signal Processing Magazine. 2026. Vol. 43, num. 3, p. 21 – 36. DOI : 10.1109/msp.2026.3667310.Sequence Modeling Architectures: Foundations [Special Issue on the Mathematics of Deep Learning]
IEEE Signal Processing Magazine. 2026. Vol. 43, num. 3, p. 115 – 129. DOI : 10.1109/msp.2026.3682808.Convergence to Equilibrium of No-Regret Dynamics in Congestion Games
2026. 20th International Conference on Web and Internet Economics, Edinburgh, UK, 2024-12-02 – 2024-12-05. p. 513 – 529. DOI : 10.1007/978-3-032-08560-3_29.ESLM: Risk-Averse Selective Language Modeling with Hierarchical Batch Selection
Transactions on Machine Learning Research. 2026. Vol. 2026-August.Diffusion-based Cumulative Adversarial Purification for Vision Language Models
Transactions on Machine Learning Research. 2026. Vol. 2026-June.Optimization in Modern Machine Learning: Steepest Descent Theory and Trustworthy Models
Lausanne, EPFL, 2026.Theoretical Studies of Learning in Overparameterized Neural Networks
Lausanne, EPFL, 2026.Reward is not enough: Advances in reinforcement learning fromdemonstrations and preferences
Lausanne, EPFL, 2026.Noisy Gradient Descent in Machine Learning: generalization, games, and sampling
Lausanne, EPFL, 2026.Character-level Adversarial Robustness in Natural Language Processing
Lausanne, EPFL, 2026.Stable Optimization in Deep Learning: Geometry and Games
Lausanne, EPFL, 2026.Scalable Neurotherapies with Bayesian Optimization and Beyond
Lausanne, EPFL, 2026.Generalized Gradient Norm Clipping & Non-Euclidean (L 0 , L 1 )-Smoothness
2025. 39th Conference on Neural Information Processing Systems, San Diego, USA, 2025-12-02 – 2025-12-07. p. 23988 – 24026. DOI : 10.52202/085713-0714.Robustness in Both Domains: CLIP Needs a Robust Text Encoder
2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.Linear Attention for Efficient Bidirectional Sequence Modeling
2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.Ascent Fails to Forget
2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.Multi-Step Alignment as Markov Games: An Optimistic Online Mirror Descent Approach with Convergence Guarantees
Transactions on Machine Learning Research. 2025. num. 12/2025.Access map
Additional links