AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points

Yi Wang, Zhiren Wang

ICML 2022 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima

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 the normalized (spherical) SGD with constant effective learning rate instead of unnormalized dynamicsSGD with constant effective learning rate on sphere · Toy function (d=100)time to equilibrium scaling in zetaImproved
Equilibrium reached within O(ζ^-1) time rather than the O(λe^-1) boundUnderparametrized CNN on MNIST · MNIST d=332time to equilibriumNo clear effect
Overparametrized network with many basins: equilibria from different initial positions remain far apartOverparametrized CNN on MNIST (d≈100k) · MNIST d≈100kmean squared distance between equilibria from different initializations (V12)Mixed

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