AI Paper Atlas

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

Analytic Insights into Structure and Rank of Neural Network Hessian Maps

Sidak Pal Singh, Gregor Bachmann, Thomas Hofmann

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Generalization theory of deep networks · 4 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 the linear-network rank formula to choose the Hessian approximation rankReLU network Hessian · ReLU network (setting unspecified)relative reconstruction error: 0.002% errorImproved
Increase network width and depthNeural network architectures · Simulated architecturesrank/number of parametersMixed
Enable biasDeep linear network · Simulated architectures across depthrank/number of parametersHurt
Train toward convergence so the residual covariance approaches zeroDeep neural network · Trainingfunctional Hessian rankHurt

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