Research

Paper

TESTING March 10, 2026

A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method

Authors

Yuchen Fang, Jihun Kim, Sen Na, James Demmel, Javad Lavaei

Abstract

In this paper, we propose a trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method for solving optimization problems with a stochastic objective and deterministic nonlinear equality and inequality constraints. In this setting, exact evaluations of the objective function and its gradient are unavailable, but their stochastic estimates can be constructed. In particular, at each iteration our method builds stochastic oracles, which estimate the objective value and gradient to satisfy proper adaptive accuracy conditions with a fixed probability. To handle inequality constraints, we adopt an interior-point method (IPM), in which the barrier parameter follows a prescribed decaying sequence. Under standard assumptions, we establish global almost-sure convergence of the proposed method to first-order stationary points. We implement the method on a subset of problems from the CUTEst test set, as well as on logistic regression problems, to demonstrate its practical performance.

Metadata

arXiv ID: 2603.10230
Provider: ARXIV
Primary Category: math.OC
Published: 2026-03-10
Fetched: 2026-03-12 04:21

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.10230v1</id>\n    <title>A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method</title>\n    <updated>2026-03-10T21:03:33Z</updated>\n    <link href='https://arxiv.org/abs/2603.10230v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.10230v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>In this paper, we propose a trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method for solving optimization problems with a stochastic objective and deterministic nonlinear equality and inequality constraints. In this setting, exact evaluations of the objective function and its gradient are unavailable, but their stochastic estimates can be constructed. In particular, at each iteration our method builds stochastic oracles, which estimate the objective value and gradient to satisfy proper adaptive accuracy conditions with a fixed probability. To handle inequality constraints, we adopt an interior-point method (IPM), in which the barrier parameter follows a prescribed decaying sequence. Under standard assumptions, we establish global almost-sure convergence of the proposed method to first-order stationary points. We implement the method on a subset of problems from the CUTEst test set, as well as on logistic regression problems, to demonstrate its practical performance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.OC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.NA'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <published>2026-03-10T21:03:33Z</published>\n    <arxiv:primary_category term='math.OC'/>\n    <author>\n      <name>Yuchen Fang</name>\n    </author>\n    <author>\n      <name>Jihun Kim</name>\n    </author>\n    <author>\n      <name>Sen Na</name>\n    </author>\n    <author>\n      <name>James Demmel</name>\n    </author>\n    <author>\n      <name>Javad Lavaei</name>\n    </author>\n  </entry>"
}