Pré-Publication, Document De Travail Année : 2026

Complexity reduction in online stochastic Newton methods with potential O(N d) total cost

Résumé

Optimizing smooth convex functions in stochastic settings, where only noisy estimates of gradients and Hessians are available, is a fundamental problem in optimization. While first-order methods possess a low per-iteration cost, their convergence is slow for ill-conditioned problems. Stochastic Newton methods utilize second-order information to correct for local curvature, but the O(d 3 ) per-iteration cost of computing and inverting a full Hessian, where d is the problem dimension, is prohibitive in high dimensions. This paper introduces an online mini-batch stochastic Newton algorithm. The method employs a random masking strategy that selects a subset of Hessian columns at each iteration, substantially reducing the per-step computational cost. This approach allows the algorithm, in the mini-batch setting, to achieve a total computational cost for a single pass over N data points of O(N d), which is comparable to first-order methods while retaining the advantages of second-order information. We establish the almost sure convergence and asymptotic efficiency of the resulting estimator. This property is obtained without requiring iterate averaging, which distinguishes this work from prior analyses.

Fichier principal
Vignette du fichier
0_main.pdf (683.85 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05493562 , version 1 (04-02-2026)

Licence

Identifiants

Citer

Antoine Godichon-Baggioni, Bruno Portier, Guillaume Sallé. Complexity reduction in online stochastic Newton methods with potential O(N d) total cost. 2026. ⟨hal-05493562⟩
134 Consultations
50 Téléchargements

Altmetric

Partager

  • More