Variational latent discrete representation for time series modelling

TL;DR

This paper introduces a variational model with a Markov chain-based discrete latent space for time series, enabling efficient training and improved interpretability, demonstrated on building and electricity datasets.

Contribution

It proposes a novel discrete latent space model using a Markov chain for end-to-end training in time series modeling.

Findings

Effective on building management data

Performs well on Electricity Transformer Dataset

Facilitates interpretability of latent representations

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.