AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Leveraging the two-timescale regime to demonstrate convergence of neural networks

Pierre Marion, Raphaël Berthier

NeurIPS 2023 · Optimization › Implicit bias and generalization · approach: Gradient flow and mean-field dynamics · 0 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 two-timescale regime (inner-layer step size much smaller than outer-layer, epsilon = 2e-5) instead of epsilon = 1 (ablation)one-pass SGD on shallow sigmoid network, m moderate · 1D piecewise-constant target recoveryrecovery of target discontinuities (qualitative)Improved
set epsilon = 1 so all neurons move toward discontinuities (ablation)SGD, shallow network · 1D piecewise-constant targetcoverage of discontinuities by neuronsHurt
use two-timescale regime, giving sparse representation where only neurons nearest discontinuities moveSGD, shallow network · 1D piecewise-constant targetnumber of active neuronsImproved
compare SGD with eta = 4e-3 to gradient flow in two-timescale limit with eta = 0SGD, two-timescale regime · 1D piecewise-constant target, loss vs stepsloss LNo clear effect
nonzero eta (sharpness) in SGD versus eta = 0 gradient flowSGD vs two-timescale limit · 1D piecewise-constant targetfinal errorHurt
apply two-timescale regime to d-dimensional cuboid piecewise-constant targets (d=2, 10) (ablation)SGD, shallow network · 2D/10D piecewise-constant targetcoverage of discontinuitiesImproved
use ReLU activations with piecewise-affine targets under two-timescale regimeSGD, shallow ReLU network · piecewise-affine targetrecovery (qualitative)Improved

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