arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02201cs.LGmath.OC
收藏

神经模拟退火

Neural Simulated Annealing

Eindhoven University of Technology(埃因霍温理工大学);Qualcomm AI Research(高通人工智能研究中心);Qualcomm Technologies Netherlands B.V.(高通技术荷兰有限公司)

Alvaro H. C. Correia, Daniel E. Worrall, Roberto Bondesan

AI总结:

本文从强化学习视角将模拟退火的提议分布视为可学习策略,提出神经模拟退火,用小型等变神经网络参数化,在多个优化问题上优于基线,且能泛化到大规模问题。

摘要:

模拟退火(SA)是一种随机全局优化技术,适用于广泛的离散和连续变量问题。尽管其简单,但针对给定问题开发有效的SA优化器依赖于少数精心挑选的组件,即邻居提议分布和温度退火调度。在这项工作中,我们从强化学习的角度审视SA,并将提议分布视为一种策略,该策略可以在给定计算预算下针对更高的解质量进行优化。我们证明,这种具有学习到的提议分布的神经SA,由小型等变神经网络参数化,在多个问题上优于SA基线:Rosenbrock函数、背包问题、装箱问题和旅行商问题。我们还表明,神经SA能够很好地扩展到大规模问题——泛化到比训练时所见问题大得多的问题——同时在解质量和墙钟时间方面达到与流行的现成求解器和其他机器学习方法相当的性能。

英文摘要:

Simulated annealing (SA) is a stochastic global optimisation technique applicable to a wide range of discrete and continuous variable problems. Despite its simplicity, the development of an effective SA optimiser for a given problem hinges on a handful of carefully handpicked components; namely, neighbour proposal distribution and temperature annealing schedule. In this work, we view SA from a reinforcement learning perspective and frame the proposal distribution as a policy, which can be optimised for higher solution quality given a fixed computational budget. We demonstrate that this Neural SA with such a learnt proposal distribution, parametrised by small equivariant neural networks, outperforms SA baselines on a number of problems: Rosenbrock's function, the Knapsack problem, the Bin Packing problem, and the Travelling Salesperson problem. We also show that Neural SA scales well to large problems - generalising to significantly larger problems than the ones seen during training - while achieving comparable performance to popular off-the-shelf solvers and other machine learning methods in terms of solution quality and wall-clock time.

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。

↑