pith. sign in

Understanding the training of infinitely deep and wide ResNets with conditional optimal transport.Communications on Pure and Applied Mathematics, 78(11):2149–2205, 2025

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

1 Pith paper citing it

fields

math.OC 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Training Infinitely Deep and Wide Transformers

math.OC · 2026-05-17 · unverdicted · novelty 8.0

Develops a mean-field neural PDE model for transformer training, proves forward-pass well-posedness via function-space ODEs, derives conditional Wasserstein gradients, and shows global convergence of gradient flow under an NTK injectivity condition equivalent to linear independence of log-sum-exp fu

citing papers explorer

Showing 1 of 1 citing paper.

  • Training Infinitely Deep and Wide Transformers math.OC · 2026-05-17 · unverdicted · none · ref 10

    Develops a mean-field neural PDE model for transformer training, proves forward-pass well-posedness via function-space ODEs, derives conditional Wasserstein gradients, and shows global convergence of gradient flow under an NTK injectivity condition equivalent to linear independence of log-sum-exp fu