Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Choi, Michael C. H."'
Autor:
Wang, Youjia, Choi, Michael C. H.
We investigate the cutoff phenomenon for Markov processes under information divergences such as $f$-divergences and R\'enyi divergences. We classify most common divergences into four types, namely $L^2$-type, $\mathrm{TV}$-type, separation-type and $
Externí odkaz:
http://arxiv.org/abs/2407.06982
We introduce a framework rooted in a rate distortion problem for Markov chains, and show how a suite of commonly used Markov Chain Monte Carlo (MCMC) algorithms are specific instances within it, where the target stationary distribution is controlled
Externí odkaz:
http://arxiv.org/abs/2404.12589
Autor:
Wang, Youjia, Choi, Michael C. H.
In this paper, we first introduce and define several new information divergences in the space of transition matrices of finite Markov chains which measure the discrepancy between two Markov chains. These divergences offer natural generalizations of c
Externí odkaz:
http://arxiv.org/abs/2312.04863
Autor:
Choi, Michael C. H., Wolfer, Geoffrey
Consider the following two-person mixed strategy game of a probabilist against Nature with respect to the parameters $(f, \mathcal{B},\pi)$, where $f$ is a convex function satisfying certain regularity conditions, $\mathcal{B}$ is either the set $\{L
Externí odkaz:
http://arxiv.org/abs/2310.04115
Autor:
Choi, Michael C. H., Wolfer, Geoffrey
Given a target distribution $\pi$ and an arbitrary Markov infinitesimal generator $L$ on a finite state space $\mathcal{X}$, we develop three structured and inter-related approaches to generate new reversiblizations from $L$. The first approach hinge
Externí odkaz:
http://arxiv.org/abs/2303.03650
Autor:
Choi, Michael C. H., Wang, Youjia
Given a target function $H$ to minimize or a target Gibbs distribution $\pi_{\beta}^0 \propto e^{-\beta H}$ to sample from in the low temperature, in this paper we propose and analyze Langevin Monte Carlo (LMC) algorithms that run on an alternative l
Externí odkaz:
http://arxiv.org/abs/2302.03973
Autor:
Choi, Michael C. H.
Given a target Gibbs distribution $\pi^0_{\beta} \propto e^{-\beta \mathcal{H}}$ to sample from in the low-temperature regime on $\Sigma_N := \{-1,+1\}^N$, in this paper we propose and analyze Metropolis dynamics that instead target an alternative di
Externí odkaz:
http://arxiv.org/abs/2208.10054
Autor:
Choi, Michael C. H., Zhang, Jing
Given a target distribution $\mu \propto e^{-\mathcal{H}}$ to sample from with Hamiltonian $\mathcal{H}$, in this paper we propose and analyze new Metropolis-Hastings sampling algorithms that target an alternative distribution $\mu^f_{1,\alpha,c} \pr
Externí odkaz:
http://arxiv.org/abs/2111.02675
Autor:
Choi, Michael C. H.
In this paper, we propose new Metropolis-Hastings and simulated annealing algorithms on finite state space via modifying the energy landscape. The core idea of landscape modification rests on introducing a parameter $c$, in which the landscape is mod
Externí odkaz:
http://arxiv.org/abs/2011.09680
Autor:
Choi, Michael C. H.
Inspired by the work of [Fang et al.. An improved annealing method and its large-time behaviour. Stochastic Process. Appl. (1997), Volume 71 Issue 1 Page 55-74.], who propose an improved simulated annealing algorithm based on a variant of overdamped
Externí odkaz:
http://arxiv.org/abs/2009.00195