Guardado en:
Detalles Bibliográficos
Autores principales: Gao, Xi, Xiong, Jinxin, Wang, Akang, Duan, Qihong, Xue, Jiang, Shi, Qingjiang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.15731
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917810393841664
author Gao, Xi
Xiong, Jinxin
Wang, Akang
Duan, Qihong
Xue, Jiang
Shi, Qingjiang
author_facet Gao, Xi
Xiong, Jinxin
Wang, Akang
Duan, Qihong
Xue, Jiang
Shi, Qingjiang
contents Solving constrained nonlinear programs (NLPs) is of great importance in various domains such as power systems, robotics, and wireless communication networks. One widely used approach for addressing NLPs is the interior point method (IPM). The most computationally expensive procedure in IPMs is to solve systems of linear equations via matrix factorization. Recently, machine learning techniques have been adopted to expedite classic optimization algorithms. In this work, we propose using Long Short-Term Memory (LSTM) neural networks to approximate the solution of linear systems and integrate this approximating step into an IPM. The resulting approximate NLP solution is then utilized to warm-start an interior point solver. Experiments on various types of NLPs, including Quadratic Programs and Quadratically Constrained Quadratic Programs, show that our approach can significantly accelerate NLP solving, reducing iterations by up to 60% and solution time by up to 70% compared to the default solver.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15731
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Gao, Xi
Xiong, Jinxin
Wang, Akang
Duan, Qihong
Xue, Jiang
Shi, Qingjiang
Optimization and Control
Solving constrained nonlinear programs (NLPs) is of great importance in various domains such as power systems, robotics, and wireless communication networks. One widely used approach for addressing NLPs is the interior point method (IPM). The most computationally expensive procedure in IPMs is to solve systems of linear equations via matrix factorization. Recently, machine learning techniques have been adopted to expedite classic optimization algorithms. In this work, we propose using Long Short-Term Memory (LSTM) neural networks to approximate the solution of linear systems and integrate this approximating step into an IPM. The resulting approximate NLP solution is then utilized to warm-start an interior point solver. Experiments on various types of NLPs, including Quadratic Programs and Quadratically Constrained Quadratic Programs, show that our approach can significantly accelerate NLP solving, reducing iterations by up to 60% and solution time by up to 70% compared to the default solver.
title IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
topic Optimization and Control
url https://arxiv.org/abs/2410.15731