AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Subquadratic Overparameterization for Shallow Neural Networks

Chaehwan Song, Ali Ramezani-Kebrya, Thomas Pethick, Armin Eftekhari, Volkan Cevher

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 2 citations (OpenAlex)

Read the paper

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 the initialization ratio \omega_2/\omega_1 while fixing the product \omega_1\omega_2Student shallow networks · MNIST teacher-student setupgeneralization errorImproved
Make the initialization ratio \omega_2/\omega_1 tend to zeroShallow neural networks · Lazy-training analysisdistance from the linearized training trajectoryHurt
Make the initialization ratio \omega_2/\omega_1 tend to infinityShallow neural networks · Lazy-training analysisdistance from the linearized training trajectoryImproved

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