Thomas Pethick

According to our database1, Thomas Pethick authored at least 8 papers between 2021 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Revisiting adversarial training for the worst-performing class.
Trans. Mach. Learn. Res., 2023

Federated Learning under Covariate Shifts with Generalization Guarantees.
CoRR, 2023

Stable Nonconvex-Nonconcave Training via Linear Interpolation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Solving stochastic weak Minty variational inequalities without increasing batch size.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Finding Actual Descent Directions for Adversarial Training.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Subquadratic Overparameterization for Shallow Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sifting through the noise: Universal first-order methods for stochastic variational inequalities.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021


  Loading...