AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Deep Limits and a Cut-Off Phenomenon for Neural Networks

Benny Avelin, Anders Karlsson

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional asymptotic generalization

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
increase network width from 1 to 2random tanh network · TV distance to point mass at 0mixing time: 9 -> 11Hurt
replace TanH with SiLU activationrandom network · TV distance to point mass at 0mixing time: 11 -> 7Mixed
use non-smooth ReLU activationrandom network · cut-off phenomenonpresence of cut-offHurt
use heuristic 1/sqrt(N) uniform weight scalingrandom tanh network · cut-off depthlayers to cut-off: 3 to 10No clear effect
normalize weights with sqrt(3)/sqrt(N) insteadrandom tanh network · cut-off depthlayers to cut-offMixed

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