AI Paper Atlas

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

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Hugo Cui, Florent Krzakala, Lenka Zdeborova

ICML 2023 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional asymptotic generalization · 6 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 optimally regularized ridge regression instead of other estimatorsDeep extensive-width random network regression · Proportional regimemean squared errorNo clear effect
Use optimally regularized kernel regression instead of other estimatorsDeep extensive-width random network regression · Proportional regimemean squared errorNo clear effect
Use random features regression rather than the original input-space linear estimatorDeep extensive-width random network regression · Proportional regimemean squared errorHurt
Use logistic regression rather than Bayes-optimal inferenceDeep extensive-width random network classification · Proportional regimeclassification error: 10^{-4}Hurt
Use ridge classification rather than Bayes-optimal inferenceDeep extensive-width random network classification · Proportional regimeclassification error: 10^{-3}Hurt
Train a neural network end-to-end instead of using kernel regressionReLU target · Quadratic sample regimemean squared error: 10^{-5}; 10^3Improved
Train a neural network end-to-end instead of using ridge regressionReLU target · Quadratic sample regimemean squared error: 10^{-5}Improved
Apply the closed-form covariance recursionDeep random networks · Activation covariance, tanhrelative squared Frobenius distance: 0.005Improved
Apply the closed-form covariance recursionDeep random networks · Activation covariance, signrelative squared Frobenius distance: 0.008Improved
Apply the closed-form covariance recursionDeep random networks · Activation covariance, erfrelative squared Frobenius distance: 0.004Improved

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