Publications#

Training Deep Learning Models with Norm-Constrained LMOs
Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls and Volkan Cevher
International Conference on Machine Learning (ICML) 2025 (spotlight)
paper code


Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
Thomas Pethick, Ioannis Mavrothalassitis and Volkan Cevher
International Conference on Learning Representations (ICLR) 2025
paper


\(\nu\)SAM: Memory-Efficient Sharpness-Aware Minimization via Nuclear Norm Constraints
Thomas Pethick, Parameswaran Raman, Lenon Minorics, Mingyi Hong, Shoham Sabach and Volkan Cevher
Transactions on Machine Learning Research (TMLR) 2025
paper


SAMPa: Sharpness-aware Minimization Parallelized
Wanyun Xie, Thomas Pethick and Volkan Cevher
Neural Information Processing Systems (NeurIPS) 2024
paper code


iFedDR: Auto-Tuning Local Computation with Inexact Douglas-Rachford Splitting in Federated Learning
Thomas Pethick, Puya Latafat, Basile Lewandowski, Zheng Xu, Peter Kairouz, Panagiotis Patrinos, Volkan Cevher
paper


Improving SAM Requires Rethinking its Optimization Formulation
Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher
International Conference on Machine Learning (ICML) 2024
paper code


Mixed Nash for Robust Federated Learning
Wanyun Xie, Thomas Pethick, Ali Ramezani-Kebrya, Volkan Cevher
Transactions on Machine Learning Research (TMLR) 2024
paper


Stable nonconvex-nonconcave training via linear interpolation
Thomas Pethick, Wanyun Xie, Volkan Cevher
Neural Information Processing Systems (NeurIPS) 2023 (spotlight)
paper code


Solving stochastic weak Minty variational inequalities without increasing batch size
Thomas Pethick, Olivier Fercoq, Puya Latafat, Panagiotis Patrinos and Volkan Cevher
International Conference on Learning Representations (ICLR) 2023
paper code


Federated Learning under Covariate Shifts with Generalization Guarantees
Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick, Grigorios Chrysos, Volkan Cevher
Transactions on Machine Learning Research (TMLR) 2023
paper code


Finding actual descent directions for adversarial training
Fabian Latorre, Igor Krawczuk, Leello Tadesse Dadi, Thomas Pethick and Volkan Cevher
International Conference on Learning Representations (ICLR) 2023
paper


Revisiting adversarial training for the worst-performing class
Thomas Pethick and Grigorios Chrysos and Volkan Cevher
Transactions on Machine Learning Research (TMLR) 2022
paper code


Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
Thomas Pethick, Puya Latafat, Panagiotis Patrinos, Olivier Fercoq, Volkan Cevher
The International Conference on Learning Representations (ICLR) 2022 (spotlight)
paper code


Sifting through the noise: Universal first-order methods for stochastic variational inequalities
Kimon Antonakopoulos, Thomas Pethick, Ali Kavis, Panayotis Mertikopoulos, Volkan Cevher
Neural Information Processing Systems (NeurIPS) 2021
paper code


Subquadratic Overparameterization for Shallow Neural Networks
Chaehwan Song, Ali Ramezani-Kebrya, Thomas Pethick, Armin Eftekhari, Volkan Cevher
Neural Information Processing Systems (NeurIPS) 2021
paper code