On Last-Iterate Convergence Beyond Zero-Sum Games

03/22/2022
by   Ioannis Anagnostides, et al.
0

Most existing results about last-iterate convergence of learning dynamics are limited to two-player zero-sum games, and only apply under rigid assumptions about what dynamics the players follow. In this paper we provide new results and techniques that apply to broader families of games and learning dynamics. First, we use a regret-based analysis to show that in a class of games that includes constant-sum polymatrix and strategically zero-sum games, dynamics such as optimistic mirror descent (OMD) have bounded second-order path lengths, a property which holds even when players employ different algorithms and prediction mechanisms. This enables us to obtain O(1/√(T)) rates and optimal O(1) regret bounds. Our analysis also reveals a surprising property: OMD either reaches arbitrarily close to a Nash equilibrium, or it outperforms the robust price of anarchy in efficiency. Moreover, for potential games we establish convergence to an ϵ-equilibrium after O(1/ϵ^2) iterations for mirror descent under a broad class of regularizers, as well as optimal O(1) regret bounds for OMD variants. Our framework also extends to near-potential games, and unifies known analyses for distributed learning in Fisher's market model. Finally, we analyze the convergence, efficiency, and robustness of optimistic gradient descent (OGD) in general-sum continuous games.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/22/2022

Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games

We show that, for any sufficiently small fixed ϵ > 0, when both players ...
04/25/2022

Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games

In this paper we establish efficient and uncoupled learning dynamics so ...
03/26/2022

Robust No-Regret Learning in Min-Max Stackelberg Games

The behavior of no-regret learning algorithms is well understood in two-...
10/31/2017

Training GANs with Optimism

We address the issue of limit cycling behavior in training Generative Ad...
02/12/2018

Let's be honest: An optimal no-regret framework for zero-sum games

We revisit the problem of solving two-player zero-sum games in the decen...
09/30/2020

Solving Zero-Sum Games through Alternating Projections

In this work, we establish near-linear and strong convergence for a natu...
02/15/2022

Provably convergent quasistatic dynamics for mean-field two-player zero-sum games

In this paper, we study the problem of finding mixed Nash equilibrium fo...