AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

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

Guodong Zhang, Xuchan Bao, Laurent Lessard, Roger Grosse

JMLR 2021 · Optimization › Nonconvex and smooth optimization · approach: Equilibrium learning in zero-sum games · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add off-by-one pointwise IQCs to the sector IQCs when analyzing OG (ablation)OG · smooth strongly-monotone gamescertified convergence rate: rho >= 1 with sector IQCs only; improves bound by roughly a factor of 4Improved
tune OG step size much smaller than 1/4L under sector IQCs onlyOG · time-varying vector fielditeration complexityNo clear effect
use proximal point analysis via IQC rather than prior boundPPM · smooth strongly-monotone gamesconvergence rate rho^2: 1/(1 + eta m) -> 1/(1 + 2 eta m)Improved
search over one-step-memory algorithm family parameters alpha, betaone-step memory algorithms · kappa = 100convergence rate: optimal alpha = 1, beta = 0No clear effect
use negative momentum with tuned beta and step sizenegative momentum · smooth strongly-monotone games, globaliteration complexity slope in kappa: slope of 1.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy