Yang Cai
Yang Cai
Home
Publications
Teaching
Short Bio
Students
Contact
Light
Dark
Automatic
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
Yang Cai
,
Gabriele Farina
,
Julien Grand-Clément
,
Christian Kroer
,
Chung-Wei Lee
,
Haipeng Luo
,
Weiqiang Zheng
December 2024
arxiv
Type
Conference paper
Publication
The 38th Conference on Neural Information Processing Systems (NeurIPS)
two-player zero-sum games
forgetful algorithms
multiplicative weights update
optimistic follow-the-regularized-leader
last-iterate convergence
Yang Cai
Associate Professor
Related
On Tractable Φ-Equilibria in Non-Concave Games
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback
Doubly Optimal No-Regret Learning in Monotone Games
Accelerated Single-Call Methods for Constrained Min-Max Optimization
Finite-Time Last-Iterate Convergence for Learning in Multi-Player Games
Cite
×