Short bio#

I am currently finishing my PhD at EPFL in the LIONS lab with Prof. Volkan Cevher, where I’ve broadly been interested in optimization for machine learning with a focus on stable training of deep learning models. During my studies, I interned with Amazon and ETH Zürich.

Selected publications#

See publications for other publications and Google Scholar for the most up to date version.

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


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


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


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


Content#

A geometric view on optimization

Online learning

Talks

Tidbits

All the posts can also be found in chronological order in the archive.


Open source#

Some of the projects I worked on prior to the PhD:

… and more on Github including this site which was originally build by Hakyll with some added \(\text{\LaTeX}\) goods. I have since moved to the Executable Book Project for a well-maintained codebase with many of the same features.