English

Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization

Optimization and Control 2025-07-16 v1 Artificial Intelligence Numerical Analysis Numerical Analysis

Abstract

Two OFFO (Objective-Function Free Optimization) noise tolerant algorithms are presented that handle bound constraints, inexact gradients and use second-order information when available.The first is a multi-level method exploiting a hierarchical description of the problem and the second is a domain-decomposition method covering the standard addditive Schwarz decompositions. Both are generalizations of the first-order AdaGrad algorithm for unconstrained optimization. Because these algorithms share a common theoretical framework, a single convergence/complexity theory is provided which covers them both. Its main result is that, with high probability, both methods need at most O(ϵ2)O(\epsilon^{-2}) iterations and noisy gradient evaluations to compute an ϵ\epsilon-approximate first-order critical point of the bound-constrained problem. Extensive numerical experiments are discussed on applications ranging from PDE-based problems to deep neural network training, illustrating their remarkable computational efficiency.

Keywords

Cite

@article{arxiv.2507.11513,
  title  = {Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization},
  author = {Serge Gratton and Alena Kopaničáková and Philippe Toint},
  journal= {arXiv preprint arXiv:2507.11513},
  year   = {2025}
}

Comments

33 pages

R2 v1 2026-07-01T04:02:46.276Z