Simulated annealing from continuum to discretization: a convergence analysis via the Eyring--Kramers law
Simulated annealing from continuum to discretization: a convergence analysis via the Eyring--Kramers law
复制标题
从连续到离散的模拟退火:通过 Eyring-Kramers 定律进行收敛分析
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
X. Zhou
中科院分区:
文献类型:
--
作者:
Wenpin Tang;X. Zhou
We study the convergence rate of continuous-time simulated annealing (Xt; t ≥ 0) and its discretization (xk; k = 0, 1, . . .) for approximating the global optimum of a given function f . We prove that the tail probability P(f(Xt) > min f + δ) (resp. P(f(xk) > min f+δ)) decays polynomial in time (resp. in cumulative step size), and provide an explicit rate as a function of the model parameters. Our argument applies the recent development on functional inequalities for the Gibbs measure at low temperatures – the Eyring-Kramers law. In the discrete setting, we obtain a condition on the step size to ensure the convergence.
DOI:
--
发表时间:
2019-04
期刊:
J. Mach. Learn. Res.
影响因子:
--
作者:
Xi Chen;S. Du;Xin T. Tong
通讯作者:
Xi Chen;S. Du;Xin T. Tong
影响因子:
1.4
作者:
Menz, Georg;Schlichting, André;Tang, Wenpin;Wu, Tianqi
通讯作者:
Wu, Tianqi