arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.05960cs.AI
收藏

OptVerse AI Solver 中的机器学习:设计原则与应用

Machine Learning Insides OptVerse AI Solver: Design Principles and Applications

Huawei Vancouver Research Center(华为温哥华研究中心);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Huawei Cloud EI Service Product Dept.(华为云EI服务产品部);Hong Kong Polytechnic University(香港理工大学)
Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhi… 展开作者

Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhiwu An, Muming Yang, Jianshu Li, Jie Wang, Junchi Yan, Defeng Sun, Tao Zhong, Yong Zhang, Jia Zeng, Mingxuan Yuan, Jianye Hao, Jun Yao, Kun Mao

AI总结:

本文介绍华为云 OptVerse AI Solver 如何融合生成模型、强化学习、图卷积网络与参数调优等 ML 技术,以生成实例、增强策略并提升求解性能。

摘要:

在数字技术无处不在的时代,高效的资源管理与决策在众多行业中都至关重要。为此,我们对将机器学习(ML)技术集成到华为云 OptVerse AI Solver 中进行了全面研究,旨在缓解真实世界数学规划实例稀缺的问题,并超越传统优化技术的能力。我们展示了利用生成模型生成复杂 SAT 和 MILP 实例的方法,这些模型能够反映真实问题的多方面结构。此外,我们提出了一个利用增强策略的训练框架,以在动态环境中维持求解器的效用。除数据生成与增强外,我们提出的方法还包括用于个性化求解器策略的新型 ML 驱动策略,重点介绍图卷积网络用于初始基选择、强化学习用于高级预求解和割选择等应用。此外,我们还详细说明了如何融入最先进的参数调优算法,这些算法显著提升了求解器性能。与 Cplex 和 SCIP 等传统求解器相比,我们的 ML 增强型 OptVerse AI Solver 在既有基准测试和真实场景中均展现出更优的速度与精度,从而强化了机器学习技术在数学规划求解器中的实践必要性与有效性。

英文摘要:

In an era of digital ubiquity, efficient resource management and decision-making are paramount across numerous industries. To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. Furthermore, we introduce a training framework leveraging augmentation policies to maintain solvers' utility in dynamic environments. Besides the data generation and augmentation, our proposed approaches also include novel ML-driven policies for personalized solver strategies, with an emphasis on applications like graph convolutional networks for initial basis selection and reinforcement learning for advanced presolving and cut selection. Additionally, we detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance. Compared with traditional solvers such as Cplex and SCIP, our ML-augmented OptVerse AI Solver demonstrates superior speed and precision across both established benchmarks and real-world scenarios, reinforcing the practical imperative and effectiveness of machine learning techniques in mathematical programming solvers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑