AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

On Lazy Training in Differentiable Programming

Lénaïc Chizat, Edouard Oyallon, Francis Bach

NeurIPS 2019 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 249 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
increase model scale factor alpha (move toward lazy regime)VGG-11 · CIFAR-10test accuracyHurt
increase initialization variance tau (lazy training)two-layer ReLU network, teacher-student · synthetic 100-Dtest lossHurt
use scaling 1/sqrt(m) instead of 1/m as width growstwo-layer ReLU network · synthetic d=100test errorHurt
widen CNN trained in lazy regimelinearized VGG-11 · CIFAR-10test accuracyImproved

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