Michael C. H. Choi

collaborators

2 papers

math.PR2023

Improved Langevin Monte Carlo for stochastic optimization via landscape modification

Michael C. H. Choi, Youjia Wang

Given a target function $H$ to minimize or a target Gibbs distribution $π_{β}^{0} \propto e^{- β H}$ to sample from in the low temperature, in this paper we propose and analyze Langevin…

math.PR2022

Landscape modification meets spin systems: from torpid to rapid mixing, tunneling and annealing in the low-temperature regime

Michael C. H. Choi

Given a target Gibbs distribution $π_{β}^{0} \propto e^{- β H}$ to sample from in the low-temperature regime on $Σ_{N} := {- 1, + 1}^{N}$ , in this paper we propose and analyze Metro…