Pith. sign in

The tradeoffs of large scale learning

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

Insights from Gradient Dynamics: Gradient Autoscaled Normalization

cs.LG · 2025-09-03 · reject · novelty 3.0

A hyperparameter-free gradient autoscaling method that zero-centers gradients and multiplies them by a global factor based on gradient standard deviation improves CIFAR-100 accuracy slightly on ResNets, but with weak statistical and theoretical support.

citing papers explorer

Showing 1 of 1 citing paper.

  • Insights from Gradient Dynamics: Gradient Autoscaled Normalization cs.LG · 2025-09-03 · reject · none · ref 3

    A hyperparameter-free gradient autoscaling method that zero-centers gradients and multiplies them by a global factor based on gradient standard deviation improves CIFAR-100 accuracy slightly on ResNets, but with weak statistical and theoretical support.