Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization

Bibliographic Details
Title: Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization
Authors: Frank E. Curtis, Michael J. O’Neill, Daniel P. Robinson
Source: Mathematical Programming. 205:431-483
Publication Status: Preprint
Publisher Information: Springer Science and Business Media LLC, 2023.
Publication Year: 2023
Subject Terms: Analysis of algorithms and problem complexity, 0211 other engineering and technologies, Stochastic programming, 02 engineering and technology, stochastic optimization, nonlinear optimization, sequential quadratic optimization, worst-case complexity, 49M37, 65K05, 65K10, 90C15, 90C30, 90C55, Methods of successive quadratic programming type, Complexity and performance of numerical algorithms, Numerical mathematical programming methods, Nonlinear programming, Optimization and Control (math.OC), FOS: Mathematics, Analysis of algorithms, Abstract computational complexity for mathematical programming problems, Mathematics - Optimization and Control
Description: A worst-case complexity bound is proved for a sequential quadratic optimization (commonly known as SQP) algorithm that has been designed for solving optimization problems involving a stochastic objective function and deterministic nonlinear equality constraints. Barring additional terms that arise due to the adaptivity of the monotonically nonincreasing merit parameter sequence, the proved complexity bound is comparable to that known for the stochastic gradient algorithm for unconstrained nonconvex optimization. The overall complexity bound, which accounts for the adaptivity of the merit parameter sequence, shows that a result comparable to the unconstrained setting (with additional logarithmic factors) holds with high probability.
46 pages, 0 figures
Document Type: Article
File Description: application/xml
Language: English
ISSN: 1436-4646
0025-5610
DOI: 10.1007/s10107-023-01981-1
DOI: 10.48550/arxiv.2112.14799
Access URL: http://arxiv.org/abs/2112.14799
https://zbmath.org/7829609
https://doi.org/10.1007/s10107-023-01981-1
Rights: Springer Nature TDM
CC BY
Accession Number: edsair.doi.dedup.....d13e1d47b2752f40e4aa6847d9d79524
Database: OpenAIRE
Description
ISSN:14364646
00255610
DOI:10.1007/s10107-023-01981-1