pith. sign in

arXiv preprint arXiv:2503.19859 , year=

An overview of low-rank structures in the training, adaptation of large models , author= · 2025 · arXiv 2503.19859

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

2 Pith papers citing it
read on arXiv browse 2 citing papers

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Pointwise Generalization in Deep Neural Networks

cs.LG · 2026-05-18 · unverdicted · novelty 7.0

Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.

Spectral Condition for $\mu$P under Width-Depth Scaling

cs.LG · 2026-02-28 · unverdicted · novelty 6.0

A unified spectral condition for μP under width-depth scaling reveals a transition at k=1 vs k≥2 transformations per residual block and enables stable feature learning for practical architectures like Transformers.

citing papers explorer

Showing 2 of 2 citing papers.

  • Pointwise Generalization in Deep Neural Networks cs.LG · 2026-05-18 · unverdicted · none · ref 164

    Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.

  • Spectral Condition for $\mu$P under Width-Depth Scaling cs.LG · 2026-02-28 · unverdicted · none · ref 2

    A unified spectral condition for μP under width-depth scaling reveals a transition at k=1 vs k≥2 transformations per residual block and enables stable feature learning for practical architectures like Transformers.