pith. sign in

arXiv preprint arXiv:2502.05668 , year=

The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks , author= · arXiv 2502.05668

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

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

Convergence of Continual Learning in Homogeneous Deep Networks

cs.LG · 2026-06-29 · unverdicted · novelty 6.0

Continual classification in homogeneous models is sequential projections onto margin sets, with local linear convergence under regularity properties for random and cyclic tasks, extended to regression.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Convergence of Continual Learning in Homogeneous Deep Networks cs.LG · 2026-06-29 · unverdicted · none · ref 8

    Continual classification in homogeneous models is sequential projections onto margin sets, with local linear convergence under regularity properties for random and cyclic tasks, extended to regression.