AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Nicolas Loizou, Hugo Berard, Gauthier Gidel, Ioannis Mitliagkas, Simon Lacoste-Julien

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Equilibrium learning in zero-sum games · 2 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
Combine SGDA and SHGD updates with positive weightsSCO · Strongly-monotone quadratic gamesrelative distance to optimalityMixed
Use a decreasing step-size after an initial constant-step phaseSGDA · Strongly-monotone quadratic gamesprecisionImproved
Use a decreasing step-size after an initial constant-step phaseSCO · Strongly-monotone quadratic gamesprecisionImproved
Increase the game condition numberSGDA · Strongly-monotone quadratic gamesconvergence speedHurt
Increase the game condition numberSHGD and SCO · Strongly-monotone quadratic gamesconvergence speedNo clear effect
Remove the SGDA component by setting its step size to zero (ablation)SCO · Quasi-strongly monotone variational inequalitiesconvergence rateHurt
Remove the SGDA component by setting its step size to zero (ablation)SCO · Variationally stable problems with mu=0convergence neighborhoodImproved
Remove the Hamiltonian-gradient component by setting its step size to zero (ablation)SCO · Quasi-strongly monotone variational inequalitiesconvergence rateHurt

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