English

Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models

Disordered Systems and Neural Networks 2026-05-08 v3 Machine Learning Machine Learning

Abstract

We derive a novel deterministic equivalence for the two-point function of a random matrix resolvent. Using this result, we give a unified derivation of the performance of a wide variety of high-dimensional linear models trained with stochastic gradient descent. This includes high-dimensional linear regression, kernel regression, and linear random feature models. Our results include previously known asymptotics as well as novel ones.

Keywords

Cite

@article{arxiv.2502.05074,
  title  = {Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models},
  author = {Alexander Atanasov and Blake Bordelon and Jacob A. Zavatone-Veth and Courtney Paquette and Cengiz Pehlevan},
  journal= {arXiv preprint arXiv:2502.05074},
  year   = {2026}
}

Comments

22 pages, in press at Advances in Theoretical and Mathematical Physics

R2 v1 2026-06-28T21:36:26.559Z