Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Online allocation and homogeneous partitioning for piecewise constant mean-approximation

Odalric-Ambrym Maillard 1 Alexandra Carpentier 2
2 Statistical Laboratory [Cambridge]
DPMMS - Department of Pure Mathematics and Mathematical Statistics
Abstract : In the setting of active learning for the multi-armed bandit, where the goal of a learner is to estimate with equal precision the mean of a finite number of arms, recent results show that it is possible to derive strategies based on finite-time confidence bounds that are competitive with the best possible strategy. We here consider an extension of this problem to the case when the arms are the cells of a finite partition P of a continuous sampling space X \subset \Real^d. Our goal is now to build a piecewise constant approximation of a noisy function (where each piece is one region of P and P is fixed beforehand) in order to maintain the local quadratic error of approximation on each cell equally low. Although this extension is not trivial, we show that a simple algorithm based on upper confidence bounds can be proved to be adaptive to the function itself in a near-optimal way, when |P| is chosen to be of minimax-optimal order on the class of \alpha-Hölder functions.
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00742893
Contributor : Odalric-Ambrym Maillard <>
Submitted on : Thursday, November 1, 2012 - 7:00:35 AM
Last modification on : Friday, September 18, 2020 - 6:06:02 PM
Long-term archiving on: : Saturday, December 17, 2016 - 1:58:32 AM

File

nips965supplementary.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00742893, version 1

Collections

Citation

Odalric-Ambrym Maillard, Alexandra Carpentier. Online allocation and homogeneous partitioning for piecewise constant mean-approximation. 2012. ⟨hal-00742893⟩

Share

Metrics

Record views

264

Files downloads

79