AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Annihilation of Spurious Minima in Two-Layer ReLU Networks

Yossi Arjevani, Michael Field

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 1 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
Add one neuron to the ΔS_d type I networkTwo-layer ReLU network · ΔS_d type I critical pointsHessian stability: minima -> non-degenerate saddles; (d-1)-dimensional eigenspace of descent directionsImproved
Add one neuron to the Δ(S_{d-1} × S_1) type II networkTwo-layer ReLU network · Δ(S_{d-1} × S_1) type II critical pointsHessian stability: 0.0908 -> 0.0230No clear effect
Add two neurons to the Δ(S_{d-1} × S_1) type II networkTwo-layer ReLU network · Δ(S_{d-1} × S_1) type II critical pointsHessian stability: -0.1198...; at least a (d-2)-dimensional space of descent directionsImproved

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