AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function

Lingkai Kong, Molei Tao

NeurIPS 2020 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima · 5 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
use large learning rate (0.02) instead of small (0.0005) for batch gradient descent5-16-1 MLP with leaky ReLU · UCI Airfoil Self-Noise regressionlong-time behavior of lossMixed
relax conditions on the small-scale term to a non-periodic, non-quasiperiodic functiondeterministic GD with f0=x^2/2 · synthetic multiscale objectiveergodicity and mixingNo clear effect
replace periodic small scale with two incommensurate sinusoidsdeterministic GD with f0=x^4/4 · synthetic multiscale objectiveconvergence to rescaled Gibbs distributionNo clear effect
add momentum to gradient descentdeterministic GD · synthetic multiscale objectivestochastic behavior at large learning rateNo clear effect

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