Variational Gaussian Process Diffusion Processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Verma, Prakhar, Adam, Vincent, Solin, Arno
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910344535867392
author Verma, Prakhar
Adam, Vincent
Solin, Arno
author_facet Verma, Prakhar
Adam, Vincent
Solin, Arno
contents Diffusion processes are a class of stochastic differential equations (SDEs) providing a rich family of expressive models that arise naturally in dynamic modelling tasks. Probabilistic inference and learning under generative models with latent processes endowed with a non-linear diffusion process prior are intractable problems. We build upon work within variational inference, approximating the posterior process as a linear diffusion process, and point out pathologies in the approach. We propose an alternative parameterization of the Gaussian variational process using a site-based exponential family description. This allows us to trade a slow inference algorithm with fixed-point iterations for a fast algorithm for convex optimization akin to natural gradient descent, which also provides a better objective for learning model parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2306_02066
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Variational Gaussian Process Diffusion Processes
Verma, Prakhar
Adam, Vincent
Solin, Arno
Machine Learning
Diffusion processes are a class of stochastic differential equations (SDEs) providing a rich family of expressive models that arise naturally in dynamic modelling tasks. Probabilistic inference and learning under generative models with latent processes endowed with a non-linear diffusion process prior are intractable problems. We build upon work within variational inference, approximating the posterior process as a linear diffusion process, and point out pathologies in the approach. We propose an alternative parameterization of the Gaussian variational process using a site-based exponential family description. This allows us to trade a slow inference algorithm with fixed-point iterations for a fast algorithm for convex optimization akin to natural gradient descent, which also provides a better objective for learning model parameters.
title Variational Gaussian Process Diffusion Processes
topic Machine Learning
url https://arxiv.org/abs/2306.02066