AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Topology and Geometry of Half-Rectified Network Optimization

C. Daniel Freeman, Joan Bruna

ICLR 2017 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 29 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 a half-rectified nonlinear network instead of a linear networkHalf-rectified networks · Adversarially constructed data distributionslevel-set connectednessHurt
Apply ridge regularization to a two-layer linear networkTwo-layer linear network · Empirical and oracle risklevel-set connectednessImproved
Use the Dynamic String Sampling algorithm to estimate paths between trained modelsCNNs on MNIST and CIFAR-10; LSTM on PTB · MNIST, CIFAR-10, PTB next-word predictionlevel-set connectivityImproved
Train models to lower loss or perplexityModels evaluated with Dynamic String Sampling · Polynomial regression, MNIST, CIFAR-10, PTBnormalized geodesic lengthHurt
Train models to lower loss or perplexityModels evaluated with Dynamic String Sampling · Polynomial regression, MNIST, CIFAR-10, PTBnumber of intermediate beadsHurt

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