AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization

Mufan Bill Li, Mihai Nica, Daniel M. Roy

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width

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
Simulate the covariance SDE instead of the finite-width Markov chainNeural Covariance SDE · Shaped networks at initializationsimulation costImproved
Compare SDE predictions with simulated finite networksNeural Covariance SDE · Shaped ReLU-like and softplus networksmatch to output covariance distributionImproved
Shape the activation function with depth-dependent scalingDeep MLP at initialization · Infinite depth-and-width limitcovariance stabilityImproved

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