Faster Rates for No-Regret Learning in General Games via Cautious Optimism
Name
3717823.3718242.pdf
Size
899.37 KB
Format
Adobe PDF
Checksum (MD5)
17fccd0734cdef3ece0ed10f62484216
Author(s)
Soleymani, Ashkan
Piliouras, Georgios
Farina, Gabriele
Date Issued
June 15, 2025
Publisher
ACM|Proceedings of the 57th Annual ACM Symposium on Theory of Computing
Citation
Ashkan Soleymani, Georgios Piliouras, and Gabriele Farina. 2025. Faster Rates for No-Regret Learning in General Games via Cautious Optimism. In Proceedings of the 57th Annual ACM Symposium on Theory of Computing (STOC '25). Association for Computing Machinery, New York, NY, USA, 518–529.
Version
Final published version
Abstract
We establish the first uncoupled learning algorithm that attains O(n log2 d logT) per-player regret in multi-player general-sum games, where n is the number of players, d is the number of actions available to each player, and T is the number of repetitions of the game. Our results exponentially improve the dependence on d compared to the O(n d logT) regret attainable by Log-Regularized Lifted Optimistic FTRL introduced by Farina, Anagnostides, Luo, Lee, Kroer, and Sandholm [2022], and also reduce the dependence on the number of iterations T from log4 T to logT compared to Optimistic Hedge, the previously well-studied algorithm with O(n logd log4 T) regret shown by Daskalakis, Fishelson, and Golowich [2021]. Our algorithm is obtained by combining the classic Optimistic Multiplicative Weights Update (OMWU) with an adaptive, non-monotonic learning rate that paces the learning process of the players, making them more cautious when their regret becomes too negative.
Description
STOC ’25, Prague, Czechia
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3717823.3718242
