OCLGMLSep 23, 2020

A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints

arXiv:2009.11359v428 citations
Originality Highly original
AI Analysis

This work provides a unified framework for certifying and optimizing convergence rates in game theory, with implications for algorithm design in multi-agent systems and optimization.

The authors tackled the problem of analyzing convergence rates for first-order methods in smooth games by adapting integral quadratic constraints (IQC) theory, achieving a global convergence rate for the negative momentum method with iteration complexity O(κ^1.5) that matches its lower bound.

The theory of integral quadratic constraints (IQCs) allows the certification of exponential convergence of interconnected systems containing nonlinear or uncertain elements. In this work, we adapt the IQC theory to study first-order methods for smooth and strongly-monotone games and show how to design tailored quadratic constraints to get tight upper bounds of convergence rates. Using this framework, we recover the existing bound for the gradient method~(GD), derive sharper bounds for the proximal point method~(PPM) and optimistic gradient method~(OG), and provide \emph{for the first time} a global convergence rate for the negative momentum method~(NM) with an iteration complexity $\mathcal{O}(κ^{1.5})$, which matches its known lower bound. In addition, for time-varying systems, we prove that the gradient method with optimal step size achieves the fastest provable worst-case convergence rate with quadratic Lyapunov functions. Finally, we further extend our analysis to stochastic games and study the impact of multiplicative noise on different algorithms. We show that it is impossible for an algorithm with one step of memory to achieve acceleration if it only queries the gradient once per batch (in contrast with the stochastic strongly-convex optimization setting, where such acceleration has been demonstrated). However, we exhibit an algorithm which achieves acceleration with two gradient queries per batch.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes