Saved in:
Bibliographic Details
Main Author: Premkumar, Akhil
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.06986
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914968504369152
author Premkumar, Akhil
author_facet Premkumar, Akhil
contents We investigate the use of diffusion models as neural density estimators. The current approach to this problem involves converting the generative process to a smooth flow, known as the Probability Flow ODE. The log density at a given sample can be obtained by solving the ODE with a black-box solver. We introduce a new, highly parallelizable method that computes log densities without the need to solve a flow. Our approach is based on estimating a path integral by Monte Carlo, in a manner identical to the simulation-free training of diffusion models. We also study how different training parameters affect the accuracy of the density calculation, and offer insights into how these models can be made more scalable and efficient.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06986
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion Density Estimators
Premkumar, Akhil
Machine Learning
We investigate the use of diffusion models as neural density estimators. The current approach to this problem involves converting the generative process to a smooth flow, known as the Probability Flow ODE. The log density at a given sample can be obtained by solving the ODE with a black-box solver. We introduce a new, highly parallelizable method that computes log densities without the need to solve a flow. Our approach is based on estimating a path integral by Monte Carlo, in a manner identical to the simulation-free training of diffusion models. We also study how different training parameters affect the accuracy of the density calculation, and offer insights into how these models can be made more scalable and efficient.
title Diffusion Density Estimators
topic Machine Learning
url https://arxiv.org/abs/2410.06986