AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Jingfeng Wu, Vladimir Braverman, Jason D. Lee

NeurIPS 2023 · Optimization › Implicit bias and generalization · approach: Implicit bias in linear networks

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
use large stepsize eta=0.1 instead of small eta=0.01GD training a 4-layer FC network · MNIST 1,000-sample subsettraining loss monotonicityHurt
use large stepsize eta=0.1 instead of small eta=0.01GD training a 4-layer FC network · MNIST 1,000-sample subsettest accuracyImproved
use stepsize eta >= 0.1 instead of eta=0.01GD for logistic regression · MNIST digits 0 vs 8, 1,000 samplesrisk monotonicityHurt
use large constant stepsize (EoS regime) instead of small stepsizeGD for logistic regression · linearly separable data (theory and simulation)long-run risk convergenceNo clear effect
replace logistic loss with exponential loss (ablation)GD with large constant stepsize · linearly separable data (theory)convergence/stabilityHurt

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