%0 Conference Paper %1 AYPSze12 %A Abbasi-Yadkori, Y. %A Pál, D. %A Szepesvári, Cs. %B AISTATS %D 2012 %K bandits bandits, learning, linear online stochastic theory, %P 1--9 %T Online-to-confidence-set conversions and application to sparse stochastic bandits %X We introduce a novel technique, which we call online-to-confidence-set conversion. The technique allows us to construct high-probability confidence sets for linear prediction with correlated inputs given the predictions of any algorithm (e.g., online LASSO, exponentiated gradient algorithm, online least-squares, p-norm algorithm) targeting online learning with linear predictors and the quadratic loss. By construction, the size of the confidence set is directly governed by the regret of the online learning algorithm. Constructing tight confidence sets is interesting on its own, but the new technique is given extra weight by the fact having access tight confidence sets underlies a number of important problems. The advantage of our construction here is that progress in constructing better algorithms for online prediction problems directly translates into tighter confidence sets. In this paper, this is demonstrated in the case of linear stochastic bandits. In particular, we introduce the sparse variant of linear stochastic bandits and show that a recent online algorithm together with our online-to-confidence-set conversion allows one to derive algorithms that can exploit if the reward is a function of a sparse linear combination of the components of the chosen action.

@inproceedings{AYPSze12, abstract = {We introduce a novel technique, which we call online-to-confidence-set conversion. The technique allows us to construct high-probability confidence sets for linear prediction with correlated inputs given the predictions of any algorithm (e.g., online LASSO, exponentiated gradient algorithm, online least-squares, p-norm algorithm) targeting online learning with linear predictors and the quadratic loss. By construction, the size of the confidence set is directly governed by the regret of the online learning algorithm. Constructing tight confidence sets is interesting on its own, but the new technique is given extra weight by the fact having access tight confidence sets underlies a number of important problems. The advantage of our construction here is that progress in constructing better algorithms for online prediction problems directly translates into tighter confidence sets. In this paper, this is demonstrated in the case of linear stochastic bandits. In particular, we introduce the sparse variant of linear stochastic bandits and show that a recent online algorithm together with our online-to-confidence-set conversion allows one to derive algorithms that can exploit if the reward is a function of a sparse linear combination of the components of the chosen action.}, added-at = {2020-03-17T03:03:01.000+0100}, author = {Abbasi-Yadkori, Y. and P{\'a}l, D. and Szepesv{\'a}ri, {Cs}.}, bibsource = {DBLP, http://dblp.uni-trier.de}, biburl = {https://www.bibsonomy.org/bibtex/2fedaf054a01a5b2bb929cd86121e55e7/csaba}, booktitle = {AISTATS}, date-added = {2012-06-03 14:18:30 -0600}, date-modified = {2015-08-02 01:02:49 +0000}, ee = {http://jmlr.csail.mit.edu/proceedings/papers/v22/abbasi-yadkori12/abbasi-yadkori12.pdf}, interhash = {01749f72c33476777e8949c7d6b7f465}, intrahash = {fedaf054a01a5b2bb929cd86121e55e7}, keywords = {bandits bandits, learning, linear online stochastic theory,}, pages = {1--9}, pdf = {papers/online-to-confidenceset.pdf}, timestamp = {2020-03-17T03:03:01.000+0100}, title = {Online-to-confidence-set conversions and application to sparse stochastic bandits}, year = 2012 }