Publications

Understanding Adam Requires Better Rotation Dependent Assumptions

NeurIPS 2025 Paper

T. H. Zhang*, L. Maes*, A. Milligan, A. Jolicoeur-Martineau, I. Mitliagkas, D. Scieur, S. Lacoste-Julien, C. Guille-Escuret

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret

ICML 2025 Paper

B. Hu, Z. Huang, T. H. Zhang, M. Lécuyer, N. Hegde

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

ICML 2025 Paper

E. Penaloza, T. H. Zhang, L. Charlin, M.E. Zarlenga

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization

ICML 2024 Paper

M. Sohrabi*, J. Ramirez*, T. H. Zhang, S. Lacoste-Julien and J. Gallego-Posada

Optimistic Thompson Sampling for Episodic Reinforcement Learning

UAI 2023 Paper Code Poster (Upperbound) Poster (UAI)

B. Hu, T. H. Zhang, N. Hegde, M. Schmidt

Thesis

Optimistic Thompson Sampling: Strategic Exploration in Bandits and Reinforcement Learning

Master's Thesis

Supervisory Committee: Mark Schmidt, Mathias Lecuyer

PDF Slides