Variational latent discrete representation for time series modelling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Variational latent discrete representation for time series modelling

Résumé

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.
Fichier principal
Vignette du fichier
main.pdf (638.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY SA - Paternité - Partage selon les Conditions Initiales

Dates et versions

hal-04140156 , version 1 (26-06-2023)
hal-04140156 , version 2 (27-06-2023)
hal-04140156 , version 3 (03-07-2023)
hal-04140156 , version 4 (28-07-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

Citer

Max Cohen, Maurice Charbit, Sylvain Le Corff. Variational latent discrete representation for time series modelling. 2023 IEEE Worshop on Statistical Signal Processing (SSP 2023), IEEE, Jul 2023, Hanoï, Vietnam. ⟨hal-04140156v4⟩
48 Consultations
82 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More