关注
Thomas Pethick
Thomas Pethick
PhD, EPFL
在 epfl.ch 的电子邮件经过验证
标题
引用次数
引用次数
年份
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
T Pethick, P Latafat, P Patrinos, O Fercoq, V Cevher
International Conference on Learning Representations, 2022
572022
Subquadratic overparameterization for shallow neural networks
C Song, A Ramezani-Kebrya, T Pethick, A Eftekhari, V Cevher
Advances in Neural Information Processing Systems 34, 11247-11259, 2021
272021
Solving stochastic weak minty variational inequalities without increasing batch size
T Pethick, O Fercoq, P Latafat, P Patrinos, V Cevher
arXiv preprint arXiv:2302.09029, 2023
242023
Sifting through the noise: Universal first-order methods for stochastic variational inequalities
K Antonakopoulos, T Pethick, A Kavis, P Mertikopoulos, V Cevher
Advances in Neural Information Processing Systems 34, 13099-13111, 2021
132021
Stable nonconvex-nonconcave training via linear interpolation
T Pethick, W Xie, V Cevher
Advances in Neural Information Processing Systems 36, 2024
62024
Revisiting adversarial training for the worst-performing class
T Pethick, GG Chrysos, V Cevher
arXiv preprint arXiv:2302.08872, 2023
32023
Federated learning under covariate shifts with generalization guarantees
A Ramezani-Kebrya, F Liu, T Pethick, G Chrysos, V Cevher
arXiv preprint arXiv:2306.05325, 2023
22023
Mixed Nash for Robust Federated Learning
W Xie, T Pethick, A Ramezani-Kebrya, V Cevher
Transactions on Machine Learning Research, 2023
22023
Improving SAM Requires Rethinking its Optimization Formulation
W Xie, F Latorre, K Antonakopoulos, T Pethick, V Cevher
arXiv preprint arXiv:2407.12993, 2024
2024
A Process Calculus for Design and Modeling of Retro-Synthesis
G Broholm, M Hammeken, MS Hansen, A Juhl, MS Larsen, JF Nilsson, ...
Information Modelling and Knowledge Bases XXX, 20-31, 2019
2019
A Simulation-based Framework for Robust Federated Learning to Training-time Attacks
W Xie, T Pethick, A Ramezani-Kebrya, V Cevher
Handling Covariate Shifts in Federated Learning with Generalization Guarantees
A Ramezani-Kebrya, F Liu, T Pethick, G Chrysos, V Cevher
Protect the weak: Class focused online learning for adversarial training
T Pethick, G Chrysos, V Cevher
系统目前无法执行此操作,请稍后再试。
文章 1–13