Prediction of individual sequences and prediction in the statistical framework : some links around sparse regression and aggregation techniques

Abstract : The topics addressed in this thesis lie in statistical machine learning. Our main framework is the prediction of arbitrary deterministic sequences (or individual sequences). It includes online learning tasks for which we cannot make any stochasticity assumption on the data to be predicted, which requires robust methods. In this work, we analyze several connections between the theory of individual sequences and the classical statistical setting, e.g., the regression model with fixed or random design, where stochastic assumptions are made. These two frameworks benefit from one another: some statistical methods can be adapted to the online learning setting to satisfy deterministic performance guarantees. Conversely, some individual-sequence techniques are useful to tune the parameters of a statistical method and to get risk bounds that are adaptive to the unknown variance. We study such connections for several connected problems: high-dimensional online linear regression under a sparsity scenario (with an application to the stochastic setting), online linear regression on L1-balls, and aggregation of nonlinear models in a model selection framework (regression on a fixed design). We also use and develop stochastic techniques to compute the minimax rates of game-theoretic online measures of performance (e.g., internal and swap regrets) in a deterministic or stochastic environment.
Document type :
Theses
General Mathematics [math.GM]. Université Paris Sud - Paris XI, 2011. English. <NNT : 2011PA112286>


https://tel.archives-ouvertes.fr/tel-00653550
Contributor : Abes Star <>
Submitted on : Monday, December 19, 2011 - 4:43:00 PM
Last modification on : Tuesday, December 20, 2011 - 9:34:56 AM

Identifiers

  • HAL Id : tel-00653550, version 1

Collections

Citation

Sébastien Gerchinovitz. Prediction of individual sequences and prediction in the statistical framework : some links around sparse regression and aggregation techniques. General Mathematics [math.GM]. Université Paris Sud - Paris XI, 2011. English. <NNT : 2011PA112286>. <tel-00653550>

Export

Share

Metrics

Consultation de
la notice

394

Téléchargement du document

185