Work

A Randomized Algorithm for Nonconvex Minimization With Inexact Evaluations and Complexity Guarantees

Year: 2025

Type: article

Abstract: We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that if an approximate direction of negative curvature is chosen as the step, we choose its sign to be positive or negative with equal probability. We allow gradients to be inexact (with a bound on their error relative to the size of the true quantity) and relax the coupling between inexactness thresholds for the first- and second-order optimality conditions. Our convergence analysis includes both an expectation bound based on martingale analysis and a high-probability bound based on concentration inequalities. We apply our algorithm to empirical risk minimization problems and obtain improved gradient sample complexity over existing works.

Source: Journal of Optimization Theory and Applications

DOI: 10.1007/s10957-025-02817-y

Authors: Shuyao Li, Stephen J. Wright

Institution: University of Wisconsin–Madison

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,190

Funders: National Science Foundation, U.S. Department of Energy, Air Force Office of Scientific Research, Argonne National Laboratory