AI Paper Atlas

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

Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model

Yiwei Shen, Pierre C Bellec

NeurIPS 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 0 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
Increase network width ratio psi_d toward infinity (overparametrization)Random-features 2-layer NN CI · Theoretical CI length, ReLU, SNR 2squared CI lengthImproved
Use small ridge penalty (interpolation) instead of larger lambda for wide networksRandom-features 2-layer NN CI · Theoretical CI length, psi_p = 1, SNR 2squared CI lengthImproved
Use activation functions with gamma_1 = 0 instead of ReLU in the high-SNR interpolating regimeRandom-features 2-layer NN CI · Infinite width limit, lambda 10^-3, SNR 2normalized squared CI length RHurt
Use ReLU rather than leaky ReLU, Swish, softplus, tanh or sigmoidRandom-features 2-layer NN CI · Infinite width limit, lambda 10^-3, SNR 2normalized squared CI length RImproved
Use gamma_1 = 0 activations instead of common activations in the low-SNR interpolating regimeRandom-features 2-layer NN CI · Infinite width limit, lambda 10^-3, SNR 0.5normalized squared CI length RImproved
Use gamma_1 = 0 activations (Pennington-Worah) to improve performanceRandom-features 2-layer NN CI · CI length across psi_p, lambda, rhonormalized squared CI length RNo clear effect

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