AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Rodrigo Veiga, Ludovic STEPHAN, Bruno Loureiro, Florent Krzakala, Lenka Zdeborova

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: Gradient flow and mean-field dynamics · 10 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
scale learning rate down with input dimension (gamma ~ d^-delta, delta>0) at fixed widthone-pass SGD, two-layer net · noisy teacher-student, kappa=0asymptotic population risk: slope -0.494 for delta=1/2Improved
grow hidden width with d so that kappa+delta>0one-pass SGD, two-layer net · teacher-student simulation d=100population riskImproved
increase learning rate with d so kappa+delta<0 (delta<0)one-pass SGD, two-layer net · teacher-student simulationpopulation riskHurt

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