Invertible Flow Non Equilibrium sampling
| Autor: | Thin, Achille, Janati, Yazid, Le Corff, Sylvain, Ollion, Charles, Doucet, Arnaud, Durmus, Alain, Moulines, Eric, Robert, Christian |
|---|---|
| Přispěvatelé: | Centre de Mathématiques Appliquées - Ecole Polytechnique (CMAP), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), Institut Polytechnique de Paris (IP Paris), Traitement de l'Information Pour Images et Communications (TIPIC-SAMOVAR), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Communications, Images et Traitement de l'Information (CITI), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Department of Statistics [Oxford], University of Oxford [Oxford], Centre de Mathématiques et de Leurs Applications (CMLA), École normale supérieure - Cachan (ENS Cachan)-Centre National de la Recherche Scientifique (CNRS), CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Department of Statistics [Warwick], University of Warwick [Coventry] |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: | |
| Popis: | 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). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|