Skip to Main content Skip to Navigation
Journal articles

Sparsity regret bounds for individual sequences in online linear regression

Sébastien Gerchinovitz 1, 2
2 CLASSIC - Computational Learning, Aggregation, Supervised Statistical, Inference, and Classification
DMA - Département de Mathématiques et Applications - ENS Paris, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt
Abstract : We consider the problem of online linear regression on arbitrary deterministic sequences when the ambient dimension d can be much larger than the number of time rounds T. We introduce the notion of sparsity regret bound, which is a deterministic online counterpart of recent risk bounds derived in the stochastic setting under a sparsity scenario. We prove such regret bounds for an online-learning algorithm called SeqSEW and based on exponential weighting and data-driven truncation. In a second part we apply a parameter-free version of this algorithm to the stochastic setting (regression model with random design). This yields risk bounds of the same flavor as in Dalalyan and Tsybakov (2011) but which solve two questions left open therein. In particular our risk bounds are adaptive (up to a logarithmic factor) to the unknown variance of the noise if the latter is Gaussian. We also address the regression model with fixed design.
Complete list of metadata

Cited literature [48 references]  Display  Hide  Download
Contributor : Sébastien Gerchinovitz Connect in order to contact the contributor
Submitted on : Friday, April 12, 2013 - 12:10:25 PM
Last modification on : Tuesday, January 11, 2022 - 11:16:24 AM
Long-term archiving on: : Saturday, July 13, 2013 - 4:03:47 AM


Files produced by the author(s)


  • HAL Id : inria-00552267, version 3
  • ARXIV : 1101.1057



Sébastien Gerchinovitz. Sparsity regret bounds for individual sequences in online linear regression. Journal of Machine Learning Research, Microtome Publishing, 2011, 14, pp.729-769. ⟨inria-00552267v3⟩



Les métriques sont temporairement indisponibles