cs.GTcs.LG
Linear Last-Iterate Convergence Rates for Optimistic Learning in Harmonic Games
📅
👥 7 authors
arXiv:2610.18560v1
Authors
John LazarsfeldAnas BarakatJacob AbernethyVidya MuthukumarGeorgios PiliourasAndre WibisonoJuba Ziani
Abstract
We prove that the last iterate of Optimistic Follow-The-Regularized-Leader (OFTRL) converges at a linear rate to a Nash equilibrium in multiplayer harmonic games. Our result holds under a mild game-regularity condition and for a large family of regularizers, including entropy, Tsallis, and log-barrier. Our analysis is based on a dual perspective of OFTRL: we prove that the interaction between optimism and the global structure of harmonic games leads to the dissipation of an energy function along the dual iterates, for which we establish tight quantitative bounds. Our result also holds for the Extragradient FTRL variant.
Paper Information
- arXiv ID:
- 2610.18560v1
- Published:
Related Categories
cs.GTcs.LG