Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

ACCEPT 1

representative citing papers

Mathematical analysis of the gradients in deep learning

cs.LG · 2025-01-26 · accept · novelty 6.0

For deep feedforward networks with piecewise-smooth activations, the autodiff gradient is shown to be the unique limit of gradients of smoothed activations, a limiting Frechet subgradient, and equal to the true gradient wherever the loss is continuously differentiable.

citing papers explorer

Showing 1 of 1 citing paper.

  • Mathematical analysis of the gradients in deep learning cs.LG · 2025-01-26 · accept · none · ref 3

    For deep feedforward networks with piecewise-smooth activations, the autodiff gradient is shown to be the unique limit of gradients of smoothed activations, a limiting Frechet subgradient, and equal to the true gradient wherever the loss is continuously differentiable.