Skip to Main content Skip to Navigation
Theses

Inferring and Predicting Dynamic Representations for Structured Temporal Data

Abstract : 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. Latent vectorial spaces allow us to learn dynamic models that are able to generate high-dimensional and structured data. First, we propose a structured latent model for spatio-temporal data forecasting. Given a set of spatial locations where data such as weather or traffic are collected, we infer latent variables for each location and use spatial structure in the dynamic function. The model is also able to discover correlations between series without prior spatial information. Next, we focus on predicting data distributions, rather than point estimates. We propose a model that generates latent variables used to condition a generative model. Text data are used to evaluate the model on diachronic language modeling. Finally, we propose a stochastic prediction model. It uses the first values of sequences to generate several possible futures. Here, the generative model is not conditioned to an absolute epoch, but to a sequence. The model is applied to stochastic video prediction.
Document type :
Theses
Complete list of metadata

https://tel.archives-ouvertes.fr/tel-03402021
Contributor : Abes Star :  Contact
Submitted on : Monday, October 25, 2021 - 3:05:17 PM
Last modification on : Monday, December 6, 2021 - 5:12:03 PM

File

DELASALLES_Edouard_2020.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03402021, version 1

Citation

Edouard Delasalles. Inferring and Predicting Dynamic Representations for Structured Temporal Data. Machine Learning [cs.LG]. Sorbonne Université, 2020. English. ⟨NNT : 2020SORUS296⟩. ⟨tel-03402021⟩

Share

Metrics

Record views

42

Files downloads

40