AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Tilting the playing field: Dynamical loss functions for machine learning

Miguel Ruiz-Garcia, Ge Zhang, Samuel S Schoenholz, Andrea J. Liu

ICML 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Generalization theory of deep networks · 6 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
Cycle class weights during training (A∼50, T∼100)Myrtle5, 64 channels · CIFAR10 validationaccuracy: ~ 0.73 -> ~ 0.79; improves up to 6%Improved
Cycle class weights (5≲A≲20, T≲300)One-hidden-layer network, width 100 · Spiral datasettraining accuracy: ~ 0.65 -> nearly perfectImproved
Cycle class weights (5≲A≲20, T≲300)One-hidden-layer network, width 100 · Spiral datasetvalidation accuracy: ~ 0.65 -> ~ 0.9Improved
Cycle class weights (5≲A≲25, T≲700)One-hidden-layer network, width 1000 · Spiral datasetgeneralization accuracyImproved
Apply oscillatory loss weightsWide Residual Network · CIFAR10 testaccuracyNo clear effect
Increase oscillation amplitude beyond the optimum (A≈30) (ablation)Dynamical loss · Classification tasksaccuracyHurt

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