Search Results for author:
Found 7 papers, 3 papers with code
Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
We prove non-asymptotic error bounds for particle gradient descent (PGD)~(Kuntz et al., 2023), a recently introduced algorithm for maximum likelihood estimation of large latent variable models obtained by discretizing a gradient flow of the free energy.
Momentum Particle Maximum Likelihood
Maximum likelihood estimation (MLE) of latent variable models is often recast as an optimization problem over the extended space of parameters and probability distributions.
Particle algorithms for maximum likelihood training of latent variable models
(Neal and Hinton, 1998) recast maximum likelihood estimation of any given latent variable model as the minimization of a free energy functional $F$, and the EM algorithm as coordinate descent applied to $F$.
Divide-and-Conquer Fusion
Many existing approaches resort to approximating the individual sub-posteriors for practical necessity, then find either an analytical approximation or sample approximation of the resulting (product-pooled) posterior.
Generalized Bayesian Filtering via Sequential Monte Carlo
We introduce a framework for inference in general state-space hidden Markov models (HMMs) under likelihood misspecification.
Bayesian model comparison with un-normalised likelihoods
Models for which the likelihood function can be evaluated only up to a parameter-dependent unknown normalising constant, such as Markov random field models, are used widely in computer science, statistical physics, spatial statistics, and network analysis.
Divide-and-Conquer with Sequential Monte Carlo
We propose a novel class of Sequential Monte Carlo (SMC) algorithms, appropriate for inference in probabilistic graphical models.
