AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

On Non-local Convergence Analysis of Deep Linear Networks

Kun Chen, Dachao Lin, Zhihua Zhang

ICML 2022 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence

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
Initialization with a1(0)+b1(0)=0 (indicator zero) versus nonzerogradient flow in deep linear networks with one-neuron layer · theory, quadratic lossconvergence to global minimizerMixed
Rank-stable set R_b(Z) initialization (s>b, u^T Z v>b) versus arbitrary balanced initgradient flow · theory, almost-sure convergenceconvergence to global minimizerImproved
Gradient descent with small learning rate in saddle-init setting versus ideal gradient flowgradient descent · synthetic deep linear net N=6, d=5escape from saddleNo 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