Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games
Name
pipis-chpipis-sm-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
937.11 KB
Format
Adobe PDF
Checksum (MD5)
44938fdcc9902560e9b325d9deb21e11
Author(s)
Pipis, Charilaos
Advisor(s)
Daskalakis, Constantinos
Farina, Gabriele
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
We propose efficient no-regret learning dynamics and ellipsoid-based methods for computing linear correlated equilibria—a relaxation of correlated equilibria and a strengthening of coarse correlated equilibria—in general convex games. These are games where the number of pure strategies is potentially exponential in the natural representation of the game, such as extensive-form games. Our work identifies linear correlated equilibria as the tightest known notion of equilibrium that is computable in polynomial time and is efficiently learnable for general convex games. Our results are enabled by a generalization of the seminal framework of Gordon et al. [2008] for Φ-regret minimization, providing extensions to this framework that can be used even when the set of deviations Φ is intractable to separate/optimize over. Our polynomial-time algorithms are similarly enabled by extending the Ellipsoid-Against-Hope approach of Papadimitriou and Roughgarden [2008] and its generalization to games of non-polynomial type proposed by Farina and Pipis [2024a]. We provide an extension to these approaches when we do not have access to the separation oracles required by these works for the dual player. This work will appear in STOC 2025, [Daskalakis et al., 2025].
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
