Liouville Flow Importance Sampler

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tian, Yifeng, Panda, Nishant, Lin, Yen Ting
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914830447804416
author Tian, Yifeng
Panda, Nishant
Lin, Yen Ting
author_facet Tian, Yifeng
Panda, Nishant
Lin, Yen Ting
contents We present the Liouville Flow Importance Sampler (LFIS), an innovative flow-based model for generating samples from unnormalized density functions. LFIS learns a time-dependent velocity field that deterministically transports samples from a simple initial distribution to a complex target distribution, guided by a prescribed path of annealed distributions. The training of LFIS utilizes a unique method that enforces the structure of a derived partial differential equation to neural networks modeling velocity fields. By considering the neural velocity field as an importance sampler, sample weights can be computed through accumulating errors along the sample trajectories driven by neural velocity fields, ensuring unbiased and consistent estimation of statistical quantities. We demonstrate the effectiveness of LFIS through its application to a range of benchmark problems, on many of which LFIS achieved state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06672
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Liouville Flow Importance Sampler
Tian, Yifeng
Panda, Nishant
Lin, Yen Ting
Machine Learning
Probability
Data Analysis, Statistics and Probability
Computation
We present the Liouville Flow Importance Sampler (LFIS), an innovative flow-based model for generating samples from unnormalized density functions. LFIS learns a time-dependent velocity field that deterministically transports samples from a simple initial distribution to a complex target distribution, guided by a prescribed path of annealed distributions. The training of LFIS utilizes a unique method that enforces the structure of a derived partial differential equation to neural networks modeling velocity fields. By considering the neural velocity field as an importance sampler, sample weights can be computed through accumulating errors along the sample trajectories driven by neural velocity fields, ensuring unbiased and consistent estimation of statistical quantities. We demonstrate the effectiveness of LFIS through its application to a range of benchmark problems, on many of which LFIS achieved state-of-the-art performance.
title Liouville Flow Importance Sampler
topic Machine Learning
Probability
Data Analysis, Statistics and Probability
Computation
url https://arxiv.org/abs/2405.06672