An objective-function-free algorithm for nonconvex stochastic optimization with deterministic equality and inequality constraints
Optimization and Control
2026-04-01 v1
Abstract
An algorithm is proposed for solving optimization problems with stochastic objective and deterministic equality and inequality constraints. This algorithm is objective-function-free in the sense that it only uses the objective's gradient and never evaluates the function value. It is based on an adaptive selection of function-decreasing and constraint-improving iterations, the first ones using an Adagrad-type stepsize. When applied to problems with full-rank Jacobian, the combined primal-dual optimality measure is shown to decrease at the rate of O(1/sqrt{k}), which is identical to the convergence rate of first-order methods in the unconstrained case.
Cite
@article{arxiv.2603.29685,
title = {An objective-function-free algorithm for nonconvex stochastic optimization with deterministic equality and inequality constraints},
author = {S. Gratton and Ph. L. Toint},
journal= {arXiv preprint arXiv:2603.29685},
year = {2026}
}