R-ParVI: Particle-based variational inference through lens of rewards

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Huang, Yongchao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916634916028416
author Huang, Yongchao
author_facet Huang, Yongchao
contents A reward-guided, gradient-free ParVI method, \textit{R-ParVI}, is proposed for sampling partially known densities (e.g. up to a constant). R-ParVI formulates the sampling problem as particle flow driven by rewards: particles are drawn from a prior distribution, navigate through parameter space with movements determined by a reward mechanism blending assessments from the target density, with the steady state particle configuration approximating the target geometry. Particle-environment interactions are simulated by stochastic perturbations and the reward mechanism, which drive particles towards high density regions while maintaining diversity (e.g. preventing from collapsing into clusters). R-ParVI offers fast, flexible, scalable and stochastic sampling and inference for a class of probabilistic models such as those encountered in Bayesian inference and generative modelling.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20482
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R-ParVI: Particle-based variational inference through lens of rewards
Huang, Yongchao
Artificial Intelligence
A reward-guided, gradient-free ParVI method, \textit{R-ParVI}, is proposed for sampling partially known densities (e.g. up to a constant). R-ParVI formulates the sampling problem as particle flow driven by rewards: particles are drawn from a prior distribution, navigate through parameter space with movements determined by a reward mechanism blending assessments from the target density, with the steady state particle configuration approximating the target geometry. Particle-environment interactions are simulated by stochastic perturbations and the reward mechanism, which drive particles towards high density regions while maintaining diversity (e.g. preventing from collapsing into clusters). R-ParVI offers fast, flexible, scalable and stochastic sampling and inference for a class of probabilistic models such as those encountered in Bayesian inference and generative modelling.
title R-ParVI: Particle-based variational inference through lens of rewards
topic Artificial Intelligence
url https://arxiv.org/abs/2502.20482