5 papers · 1 filter
A weak convergence approach to large deviations for stochastic approximations
Henrik Hult, Adam Lindhe, Pierre Nyquist +1
The theory of stochastic approximations form the theoretical foundation for studying convergence properties of many popular recursive learning algorithms in statistics, machine lea…
Almost sure convergence of the accelerated weight histogram algorithm
Henrik Hult, Guo-Jhen Wu
The accelerated weight histogram (AWH) algorithm is an iterative extended ensemble algorithm, developed for statistical physics and computational biology applications. It is used t…
Analysis and optimization of certain parallel Monte Carlo methods in the low temperature limit
Paul Dupuis, Guo-Jhen Wu
Metastability is a formidable challenge to Markov chain Monte Carlo methods. In this paper we present methods for algorithm design to meet this challenge. The design problem we con…
Large deviation properties of the empirical measure of a metastable small noise diffusion
Paul Dupuis, Guo-Jhen Wu
The aim of this paper is to develop tractable large deviation approximations for the empirical measure of a small noise diffusion. The starting point is the Freidlin-Wentzell theor…
Infinite Swapping using IID Samples
Paul Dupuis, Guo-Jhen Wu, Michael Snarski
We propose a new method for estimating rare event probabilities when independent samples are available. It is assumed that the underlying probability measures satisfy a large devia…