A sub-sampled tensor method for nonconvex optimization

DOI10.1093/IMANUM/DRAC057arXiv1911.10367OpenAlexW4302760397MaRDI QIDQ6190818FDOQ6190818

Publication date: 6 February 2024

Published in: IMA Journal of Numerical Analysis (Search for Journal in Brave)

Abstract: We present a stochastic optimization method that uses a fourth-order regularized model to find local minima of smooth and potentially non-convex objective functions with a finite-sum structure. This algorithm uses sub-sampled derivatives instead of exact quantities. The proposed approach is shown to find an

(e p s i l o n_{1}, e p s i l o n_{2}, e p s i l o n_{3})

-third-order critical point in at most

iterations, thereby matching the rate of deterministic approaches. In order to prove this result, we derive a novel tensor concentration inequality for sums of tensors of any order that makes explicit use of the finite-sum structure of the objective function.

Full work available at URL: https://arxiv.org/abs/1911.10367

zbMATH Keywords

nonlinear optimization unconstrained optimization non-convex optimization trust-region methods cubic regularization

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Nonconvex programming, global optimization (90C26)

Cited In (1)

Inexact tensor methods and their application to stochastic convex optimization

This page was built for publication: A sub-sampled tensor method for nonconvex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6190818)