atlas

Research map / Optimization / Nonconvex and smooth optimization

The Mechanics of n-Player Differentiable Games

ICML 2018 · Optimization › Nonconvex and smooth optimization · approach: Gradient descent ascent for minimax · 138 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use SGA instead of simultaneous gradient descenttwo-player zero-sum bimatrix game · zero-sum bimatrix gamelearning-rate robustness: 0.3, 1.2Helped
Use SGA instead of simultaneous gradient descentweak-attractor game with strong rotational force · weak-attractor gameconvergence speed and robustness: 0.01, 0.032, 0.1Helped
Use SGA instead of simultaneous gradient descentGAN with 16-Gaussian mixture data · 16-Gaussian mixturemode collapse: 2000, 4000, 6000, 8000Helped
Add alignment to SGA (ablation)SGA on GAN with 16-Gaussian mixture data · 16-Gaussian mixtureconvergence speedHelped
Add alignment to consensus optimization (ablation)consensus optimization · GAN experimentsperformance near unstable equilibriaHelped
Add the original game-gradient term to the consensus adjustment (ablation)simplified consensus adjustment that drops the first term · GAN experimentsperformanceHelped

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