Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Loo, Junn Yong, Adeline, Michelle, Pal, Arghya, Baskaran, Vishnu Monn, Ting, Chee-Ming, Phan, Raphael C. -W.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914880486899712
author Loo, Junn Yong
Adeline, Michelle
Pal, Arghya
Baskaran, Vishnu Monn
Ting, Chee-Ming
Phan, Raphael C. -W.
author_facet Loo, Junn Yong
Adeline, Michelle
Pal, Arghya
Baskaran, Vishnu Monn
Ting, Chee-Ming
Phan, Raphael C. -W.
contents Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence training. In this paper, we present a novel energy-based generative framework, Variational Potential Flow (VAPO), that entirely dispenses with implicit MCMC sampling and does not rely on complementary latent models or cooperative training. The VAPO framework aims to learn a potential energy function whose gradient (flow) guides the prior samples, so that their density evolution closely follows an approximate data likelihood homotopy. An energy loss function is then formulated to minimize the Kullback-Leibler divergence between density evolution of the flow-driven prior and the data likelihood homotopy. Images can be generated after training the potential energy, by initializing the samples from Gaussian prior and solving the ODE governing the potential flow on a fixed time interval using generic ODE solvers. Experiment results show that the proposed VAPO framework is capable of generating realistic images on various image datasets. In particular, our proposed framework achieves competitive FID scores for unconditional image generation on the CIFAR-10 and CelebA datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15238
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling
Loo, Junn Yong
Adeline, Michelle
Pal, Arghya
Baskaran, Vishnu Monn
Ting, Chee-Ming
Phan, Raphael C. -W.
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence training. In this paper, we present a novel energy-based generative framework, Variational Potential Flow (VAPO), that entirely dispenses with implicit MCMC sampling and does not rely on complementary latent models or cooperative training. The VAPO framework aims to learn a potential energy function whose gradient (flow) guides the prior samples, so that their density evolution closely follows an approximate data likelihood homotopy. An energy loss function is then formulated to minimize the Kullback-Leibler divergence between density evolution of the flow-driven prior and the data likelihood homotopy. Images can be generated after training the potential energy, by initializing the samples from Gaussian prior and solving the ODE governing the potential flow on a fixed time interval using generic ODE solvers. Experiment results show that the proposed VAPO framework is capable of generating realistic images on various image datasets. In particular, our proposed framework achieves competitive FID scores for unconditional image generation on the CIFAR-10 and CelebA datasets.
title Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2407.15238