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 2501.03443math.OCcs.AI
收藏

优化学习

Optimization Learning

Georgia Institute of Technology(佐治亚理工学院)

Pascal Van Hentenryck

AI总结:

本文提出优化学习框架,通过结合深度学习与修复/补全层构建可自监督端到端训练、可行且带质量保证的优化代理,并在电力系统实时风险评估和安全约束最优潮流中验证其潜力。

摘要:

本文介绍了优化学习的概念,这是一种设计优化代理的方法论,用于学习参数化优化问题的输入/输出映射。这些优化代理在设计上是可信的:它们计算底层优化问题的可行解,为返回的解提供质量保证,并可扩展到大型实例。优化代理是可微程序,将传统深度学习技术与修复或补全层相结合,以产生可行解。本文表明,优化代理可以自监督方式进行端到端训练。文中提出了提供性能保证并将优化代理扩展到大规模优化问题的方法。优化代理的潜力通过电力系统中的应用,尤其是实时风险评估和安全约束最优潮流,得到了突出展示。

英文摘要:

This article introduces the concept of optimization learning, a methodology to design optimization proxies that learn the input/output mapping of parametric optimization problems. These optimization proxies are trustworthy by design: they compute feasible solutions to the underlying optimization problems, provide quality guarantees on the returned solutions, and scale to large instances. Optimization proxies are differentiable programs that combine traditional deep learning technology with repair or completion layers to produce feasible solutions. The article shows that optimization proxies can be trained end-to-end in a self-supervised way. It presents methodologies to provide performance guarantees and to scale optimization proxies to large-scale optimization problems. The potential of optimization proxies is highlighted through applications in power systems and, in particular, real-time risk assessment and security-constrained optimal power flow.

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。

↑