Thomas Pethick

Research Interests:

  • Bayesian Optimization
  • Machine Learning

Biography

I received my Master with Honours in Computer Science and Engineering from the Technical Danish University in the summer 2019. My master project titled “Gaussian Processes for Economic Models” was jointly supervised by Prof. Ole Winther and Prof. Volkan Cehver. I started my PhD at LIONS in 2019.

Publications with LIONS

Improving SAM Requires Rethinking its Optimization Formulation

2024. 41st International Conference on Machine Learning (ICML 2024).

Stable Nonconvex-Nonconcave Training via Linear Interpolation

2023. Thirty-seventh Conference on Neural Information Processing Systems.

Finding Actual Descent Directions For Adversarial Training

2023. 11th International Conference on Learning Representations (ICLR).

Federated Learning under Covariate Shifts with Generalization Guarantees

A. Ramezani-Kebrya; F. Liu; T. M. Pethick; G. Chrysos; V. Cevher 

Transactions on Machine Learning Research. 2023. num. 06.

Revisiting adversarial training for the worst-performing class

T. M. Pethick; G. Chrysos; V. Cevher 

Transactions on Machine Learning Research. 2023. 

Solving stochastic weak Minty variational inequalities without increasing batch size

T. M. Pethick; O. Fercoq; P. Latafat; P. Patrinos; V. Cevher 

11th International Conference on Learning Representations ICLR2023, Kigali, Rwanda, May 1-5, 2023.

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

2022. 10th International Conference on Learning Representations (ICLR 2022).

Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities

2021. NeurIPS 2021 : Thirty-fifth Conference on Neural Information Processing Systems.

Subquadratic Overparameterization for Shallow Neural Networks

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).

Access map