Pith. sign in

How neural networks learn the support is an implicit regularization effect of sgd

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

representative citing papers

Does Weight Decay Enhance Training Stability?

cs.LG · 2026-05-15 · conditional · novelty 6.0

Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding more stable NTK dynamics.

citing papers explorer

Showing 2 of 2 citing papers.

  • Does Weight Decay Enhance Training Stability? cs.LG · 2026-05-15 · conditional · none · ref 6

    Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding more stable NTK dynamics.

  • Compositional Sparsity as an Inductive Bias for Neural Architecture Design cs.LG · 2026-05-14 · unverdicted · none · ref 3

    HNNs recover known sparse hierarchies on synthetic tasks and match or exceed dense DNNs on real datasets while using orders of magnitude fewer parameters and showing lower hyperparameter sensitivity.