DeepAI AI Chat
Log In Sign Up

Invertible Flow Non Equilibrium sampling

by   Achille Thin, et al.

Simultaneously sampling from a complex distribution with intractable normalizing constant and approximating expectations under this distribution is a notoriously challenging problem. We introduce a novel scheme, Invertible Flow Non Equilibrium Sampling (InFine), which departs from classical Sequential Monte Carlo (SMC) and Markov chain Monte Carlo (MCMC) approaches. InFine constructs unbiased estimators of expectations and in particular of normalizing constants by combining the orbits of a deterministic transform started from random initializations.When this transform is chosen as an appropriate integrator of a conformal Hamiltonian system, these orbits are optimization paths. InFine is also naturally suited to design new MCMC sampling schemes by selecting samples on the optimization paths.Additionally, InFine can be used to construct an Evidence Lower Bound (ELBO) leading to a new class of Variational AutoEncoders (VAE).


page 13

page 23


Unbiased Multilevel Monte Carlo methods for intractable distributions: MLMC meets MCMC

Constructing unbiased estimators from Markov chain Monte Carlo (MCMC) ou...

Approximate sampling and estimation of partition functions using neural networks

We consider the closely related problems of sampling from a distribution...

Unbiased and Consistent Nested Sampling via Sequential Monte Carlo

We introduce a new class of sequential Monte Carlo methods called Nested...

Living on the Edge: An Unified Approach to Antithetic Sampling

We identify recurrent ingredients in the antithetic sampling literature ...

Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding

Variational Autoencoders (VAEs) are a popular generative model, but one ...

Unbiased Bayes for Big Data: Paths of Partial Posteriors

A key quantity of interest in Bayesian inference are expectations of fun...

Metropolis-Hastings with Averaged Acceptance Ratios

Markov chain Monte Carlo (MCMC) methods to sample from a probability dis...