AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Nonlinear random matrix theory for deep learning

Jeffrey Pennington, Pratik Worah

NeurIPS 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Geometry of low-rank and SPD structure

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
Set zeta = E[f'(z)]^2 = 0 (activation with zero squared mean derivative, e.g., f1-f4 in Fig. 3)Gram matrix Y^T Y of single-layer nonlinear random features · Analytic limit / data covariancelimiting spectral distributionNo clear effect
Choose activation with zeta near 0 (small nonlinearity mismatch) instead of zeta near etaRandom feature ridge regression memorization · Memorization task, theory vs simulationtraining loss E_trainImproved
Propagate data covariance through deep network with activation having zeta=0 (vs zeta != 0) (ablation)Data covariance eigenvalue distribution at layer 10 · Piecewise linear relu-variant activations, width sweepdistance d between layer-1 and layer-10 eigenvalue distributionsImproved
Replace linear activation with nonlinear activation (eta=zeta not satisfied) (ablation)Random feature memorization capacity · Simulated random feature networks, beta sweeptraining loss E_trainImproved

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