pith. sign in

arxiv: 2507.11513 · v1 · pith:5YLQLIWLnew · submitted 2025-07-15 · 🧮 math.OC · cs.AI· cs.NA· math.NA

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

classification 🧮 math.OC cs.AIcs.NAmath.NA
keywords adagradalgorithmsapplicationsbound-constrainedepsilonfirst-ordermethodoptimization
0
0 comments X
read the original 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 $O(\epsilon^{-2})$ iterations and noisy gradient evaluations to compute an $\epsilon$-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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.