Pith. sign in

Title resolution pending

Wide Deep Neural Networks with Gaussian Weights are Very Close to Gaussian Processes , author= · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

Quantitative Gaussian-Process limits of Tensor Programs

cs.LG · 2026-07-07 · accept · novelty 6.0

Finite-width executions of Netsor tensor programs converge to their infinite-width Gaussian-process limits in Wasserstein distance at rate O(1/√n) per hidden width, covering weight-sharing architectures including RNNs and attention.

citing papers explorer

Showing 1 of 1 citing paper.

  • Quantitative Gaussian-Process limits of Tensor Programs cs.LG · 2026-07-07 · accept · none · ref 6

    Finite-width executions of Netsor tensor programs converge to their infinite-width Gaussian-process limits in Wasserstein distance at rate O(1/√n) per hidden width, covering weight-sharing architectures including RNNs and attention.