Guardado en:
Detalles Bibliográficos
Autores principales: Li, Sirui, Kulkarni, Janardhan, Menache, Ishai, Wu, Cathy, Li, Beibin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.08288
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916624751132672
author Li, Sirui
Kulkarni, Janardhan
Menache, Ishai
Wu, Cathy
Li, Beibin
author_facet Li, Sirui
Kulkarni, Janardhan
Menache, Ishai
Wu, Cathy
Li, Beibin
contents Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on specific problem classes and do not generalize to unseen classes. To address this shortcoming, we take a foundation model training approach, where we train a single deep learning model on a diverse set of MILP problems to generalize across problem classes. As existing datasets for MILP lack diversity and volume, we introduce MILP-Evolve, a novel LLM-based evolutionary framework that is capable of generating a large set of diverse MILP classes with an unlimited amount of instances. We study our methodology on three key learning tasks that capture diverse aspects of MILP: (1) integrality gap prediction, (2) learning to branch, and (3) a new task of aligning MILP instances with natural language descriptions. Our empirical results show that models trained on the data generated by MILP-Evolve achieve significant improvements on unseen problems, including MIPLIB benchmarks. Our work highlights the potential of moving towards a foundation model approach for MILP that can generalize to a broad range of MILP applications. Our code and data are publicly available at https://github.com/microsoft/OptiGuide.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08288
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Foundation Models for Mixed Integer Linear Programming
Li, Sirui
Kulkarni, Janardhan
Menache, Ishai
Wu, Cathy
Li, Beibin
Machine Learning
Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on specific problem classes and do not generalize to unseen classes. To address this shortcoming, we take a foundation model training approach, where we train a single deep learning model on a diverse set of MILP problems to generalize across problem classes. As existing datasets for MILP lack diversity and volume, we introduce MILP-Evolve, a novel LLM-based evolutionary framework that is capable of generating a large set of diverse MILP classes with an unlimited amount of instances. We study our methodology on three key learning tasks that capture diverse aspects of MILP: (1) integrality gap prediction, (2) learning to branch, and (3) a new task of aligning MILP instances with natural language descriptions. Our empirical results show that models trained on the data generated by MILP-Evolve achieve significant improvements on unseen problems, including MIPLIB benchmarks. Our work highlights the potential of moving towards a foundation model approach for MILP that can generalize to a broad range of MILP applications. Our code and data are publicly available at https://github.com/microsoft/OptiGuide.
title Towards Foundation Models for Mixed Integer Linear Programming
topic Machine Learning
url https://arxiv.org/abs/2410.08288