AI Paper Atlas

Research map / Optimization / Optimizers

EigenGame Unloaded: When playing games is better than optimizing

Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel

ICLR 2022 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 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
Replace α-EigenGame's update with the unbiased μ-EigenGame updateEigenGame · MNISTlongest correct eigenvector streakImproved
Replace α-EigenGame's update with the unbiased μ-EigenGame updateEigenGame · MNISTnormalized subspace distanceImproved
Increase data parallelism and effective batch sizeμ-EigenGame · Meena embeddingseigenvector recovery performance: 16,384 samples -> 65,536 samples -> 131,072 samplesImproved
Increase data parallelism and effective batch sizeα-EigenGame · Meena embeddingseigenvector recovery performance: 16,384 samples -> 65,536 samples -> 131,072 samplesNo clear effect
Use μ-EigenGame instead of α-EigenGameEigenGame · Synthetic data with exponentially decaying spectrumperformanceImproved
Use μ-EigenGame instead of α-EigenGameEigenGame · Synthetic data with linearly decaying spectrumperformanceNo clear effect
Remove the stop-gradient operation and use the true gradient of the pseudo-utility (ablation)μ-EigenGame · Eigenvector learning experimentsperformanceHurt

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