DELASALLES Edouard

PhD graduated
Team : MLIA
Departure date : 06/30/2020
https://lip6.fr/Edouard.Delasalles

Supervision : Ludovic DENOYER

Co-supervision : LAMPRIER Sylvain

Inferring and Predicting Dynamic Representations for Structured Temporal Data

Temporal data constitute a large part of data collected digitally. Predicting their next values is an important and challenging task in domains such as climatology, optimal control, or natural language processing. Standard statistical methods are based on linear models and are often limited to low-dimensional data. We instead use deep learning methods capable of handling high-dimensional structured data and leverage large quantities of examples.
In this thesis, we are interested in latent variable models. Contrary to autoregressive models that directly use past data to perform prediction, latent models infer low-dimensional vectorial representations of data on which prediction is performed.
First, we propose a structured latent model for spatiotemporal data forecasting. Next, we focus on predicting data distributions, rather than point estimates, through a diachronic language modeling task. Finally, we propose a stochastic prediction model applied to video prediction.

Defence : 06/30/2020 - 14h - Visionconférence

Jury members :

M. Alexandre Allauzen, Professeur, ESPCI - CNRS [Rapporteur]
M. Thierry Artieres, Professeur, Aix Marseille Université - Ecole Centrale Marseille - LIS [Rapporteur]
M. Ludovic Denoyer, Professeur, Sorbonne Université - LIP6 - FAIR
Mme Ahlame Douzal, Maître de Conférences (HDR), Université Grenoble Alpes - LIG
M. Patrcik Gallinari, Sorbonne Université - LIP6
M. Sylvain Lamprier, Maître de Conférences, Sorbonne Université - LIP6

2017-2020 Publications