Saved in:
Bibliographic Details
Main Authors: Zeng, Sebastian, Graf, Florian, Kwitt, Roland
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.16248
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909113828507648
author Zeng, Sebastian
Graf, Florian
Kwitt, Roland
author_facet Zeng, Sebastian
Graf, Florian
Kwitt, Roland
contents We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the challenges that arise when trying to learn an (almost arbitrary) latent neural SDE from data, such as efficient gradient computation, we take a step back and study a specific subclass instead. In our case, the SDE evolves on a homogeneous latent space and is induced by stochastic dynamics of the corresponding (matrix) Lie group. In learning problems, SDEs on the unit n-sphere are arguably the most relevant incarnation of this setup. Notably, for variational inference, the sphere not only facilitates using a truly uninformative prior, but we also obtain a particularly simple and intuitive expression for the Kullback-Leibler divergence between the approximate posterior and prior process in the evidence lower bound. Experiments demonstrate that a latent SDE of the proposed type can be learned efficiently by means of an existing one-step geometric Euler-Maruyama scheme. Despite restricting ourselves to a less rich class of SDEs, we achieve competitive or even state-of-the-art results on various time series interpolation/classification problems.
format Preprint
id arxiv_https___arxiv_org_abs_2306_16248
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Latent SDEs on Homogeneous Spaces
Zeng, Sebastian
Graf, Florian
Kwitt, Roland
Machine Learning
We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the challenges that arise when trying to learn an (almost arbitrary) latent neural SDE from data, such as efficient gradient computation, we take a step back and study a specific subclass instead. In our case, the SDE evolves on a homogeneous latent space and is induced by stochastic dynamics of the corresponding (matrix) Lie group. In learning problems, SDEs on the unit n-sphere are arguably the most relevant incarnation of this setup. Notably, for variational inference, the sphere not only facilitates using a truly uninformative prior, but we also obtain a particularly simple and intuitive expression for the Kullback-Leibler divergence between the approximate posterior and prior process in the evidence lower bound. Experiments demonstrate that a latent SDE of the proposed type can be learned efficiently by means of an existing one-step geometric Euler-Maruyama scheme. Despite restricting ourselves to a less rich class of SDEs, we achieve competitive or even state-of-the-art results on various time series interpolation/classification problems.
title Latent SDEs on Homogeneous Spaces
topic Machine Learning
url https://arxiv.org/abs/2306.16248