Variational latent discrete representation for time series modelling
Abstract
Discrete latent space models have recently achieved performance on par with their continuous counterparts in deep variational inference. While they still face various implementation challenges, these models offer the opportunity for a better interpretation of latent spaces, as well as a more direct representation of naturally discrete phenomena. Most recent approaches propose to train separately very high-dimensional prior models on the discrete latent data which is a challenging task on its own. In this paper, we introduce a latent data model where the discrete state is a Markov chain, which allows fast end-to-end training. The performance of our generative model is assessed on a building management dataset and on the publicly available Electricity Transformer Dataset.
Cite
@article{arxiv.2306.15282,
title = {Variational latent discrete representation for time series modelling},
author = {Max Cohen and Maurice Charbit and Sylvain Le Corff},
journal= {arXiv preprint arXiv:2306.15282},
year = {2023}
}
Comments
2023 IEEE Workshop on Statistical Signal Processing (SSP 2023), IEEE, Jul 2023, Hano{\"i}, Vietnam