← Search

Marylou Gabrie

2 accepted papers

2022

Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals

AISTATS 2022poster

Markov Chain Monte Carlo (MCMC) methods are a powerful tool for computation with complex probability distributions. However the performance of such methods is critically dependent on properly tuned parameters, most of which are difficult if not impossible to know a priori for a given target distribu…

2015

Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy

NeurIPS 2015poster

Restricted Boltzmann machines are undirected neural networks which have been shown tobe effective in many applications, including serving as initializations fortraining deep multi-layer neural networks. One of the main reasons for their success is theexistence of efficient and practical stochastic a…