Sparsity regret bounds for individual sequences in online linear regression
arXiv:1101.1057
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.
arXiv commentPublished in Journal of Machine Learning Research at http://www.jmlr.org/papers/volume14/gerchinovitz13a/gerchinovitz13a.pdf
References in corpus (8)
- Simultaneous analysis of Lasso and Dantzig selector
- On the conditions used to prove oracle results for the Lasso
- Fast learning rates in statistical inference through aggregation
- Exponential Screening and optimal rates of sparse estimation
- Sparse recovery in convex hulls via entropy penalization
- Aggregation for Regression Learning
- An l1-Oracle Inequality for the Lasso
- Risk bounds in linear regression through PAC-Bayesian truncation