模拟退火：连续域优化的严格有限时间保证
Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains
摘要：
模拟退火是一种用于逼近全局优化问题的解的流行方法。其性能的现有结果适用于离散组合优化，优化变量可以假设只有一个有限的可能值。我们介绍了一个新的一般配方的模拟退火，它允许一个保证有限的时间性能的优化功能的连续变量。这些结果对有界区域上的任何优化问题都是普遍适用的，并建立了模拟退火与连续区域上最新的马尔可夫链蒙特卡罗方法收敛性理论之间的联系。这项工作的灵感来自有限时间学习的概念与已知的准确性和信心发展的统计学习理论。
英文摘要：
Simulated annealing is a popular method for approaching the solution of a global optimization problem. Existing results on its performance apply to discrete combinatorial optimization where the optimization variables can assume only a finite set of possible values. We introduce a new general formulation of simulated annealing which allows one to guarantee finite-time performance in the optimization of functions of continuous variables. The results hold universally for any optimization problem on a bounded domain and establish a connection between simulated annealing and up-to-date theory of convergence of Markov chain Monte Carlo methods on continuous domains. This work is inspired by the concept of finite-time learning with known accuracy and confidence developed in statistical learning theory.
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。
