AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Multi-layer State Evolution Under Random Convolutional Design

Max Daniels, Cedric Gerbelot, Florent Krzakala, Lenka Zdeborova

NeurIPS 2022 · Architectures and efficiency › CNN design · approach: Theory of convolutional inductive bias · 1 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 random multichannel convolutional (MCC) sensing matrices instead of dense i.i.d. Gaussian matrices in AMPAMP for sparse compressive sensing · Sparse compressive sensing, P=q=1024, k=3, rho in {0.25, 0.5, 0.75}log(MSE) vs measurement ratio betaNo clear effect
Reduce convolution size q from 1024 to 10 (q much smaller than P)MCC AMP · Sparse compressive sensingagreement with dense state evolutionNo clear effect
Stack multiple layers (L = 1, 2, 3) with MCC couplings and identity channelsML-AMP · Multi-layer compressive sensing, linear activations, q=10, k=3, n(L)=5000log(MSE)No clear effect
Use ReLU channel functions instead of identity in deeper layersML-AMP with MCC layers · Multi-layer compressive sensing, ReLU activationslog(MSE)No clear effect
Vary measurement ratio beta near the recovery threshold (0.4 to 0.55) at rho = 0.25MCC AMP · Sparse compressive sensingAMP iterate convergence in log(MSE)No 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