math.NA · 2026-10-23 · No. 151

Numerical Analysis, 2026-10-23.

2 new papers in math.NA. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

2 entries
  1. 01

    Phase Transition from Random Features to Fully Trainable Networks

    Xin He, Huan Lao, Xiliang Lu, Shijun Zhang

    math.NA · cs.LG · math.ST · stat.ML

    Constructing accurate and computationally tractable approximation spaces is a fundamental task in scientific computing. Partially trainable neural networks bridge fixed random features and fully adaptive representations. This paper quantifies a phase transition pattern in approximation bounds and observes analogous behavior in training errors: a rapid but smooth initial improvement followed by diminishing returns, with a sharper transition...

    arxiv.org/abs/2610.31663 · PDF

  2. 02

    Convex Equilibrium Potentials for Monge--Ampère: Curvature Bounds and A Posteriori Evaluation

    Edison Vázquez, Yingdong Lu, Tomasz Nowicki

    math.NA · cs.LG

    Equilibrium neural networks define their hidden state as the fixed point of a contraction, so their effective depth is set at evaluation time rather than by the architecture. Using them for fully nonlinear PDEs raises two issues that explicit networks avoid: second derivatives may grow with the effective depth, and the potential is only ever evaluated approximately. We study nonnegative softplus equilibrium networks with contraction factor...

    arxiv.org/abs/2610.31386 · PDF

This edition is part of The Daily Abstract — math.NA archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.