ML Anthology

Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm

Philippe Rolet, Michèle Sebag, Olivier Teytaud
ECML-PKDD 2009 pp. 302-317
doi:10.1007/978-3-642-04174-7_20 /ecmlpkdd/2009/rolet2009ecmlpkdd-boosting/

Abstract

This paper focuses on Active Learning with a limited number of queries; in application domains such as Numerical Engineering, the size of the training set might be limited to a few dozen or hundred examples due to computational constraints. Active Learning under bounded resources is formalized as a finite horizon Reinforcement Learning problem, where the sampling strategy aims at minimizing the expectation of the generalization error. A tractable approximation of the optimal (intractable) policy is presented, the Bandit-based Active Learner ( BAAL ) algorithm. Viewing Active Learning as a single-player game, BAAL combines UCT, the tree structured multi-armed bandit algorithm proposed by Kocsis and Szepesvári (2006), and billiard algorithms. A proof of principle of the approach demonstrates its good empirical convergence toward an optimal policy and its ability to incorporate prior AL criteria. Its hybridization with the Query-by-Committee approach is found to improve on both stand-alone BAAL and stand-alone QbC.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Rolet et al. "Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009. doi:10.1007/978-3-642-04174-7_20

Markdown

[Rolet et al. "Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009.](https://mlanthology.org/ecmlpkdd/2009/rolet2009ecmlpkdd-boosting/) doi:10.1007/978-3-642-04174-7_20

BibTeX

@inproceedings{rolet2009ecmlpkdd-boosting,
  title     = {{Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm}},
  author    = {Rolet, Philippe and Sebag, Michèle and Teytaud, Olivier},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2009},
  pages     = {302-317},
  doi       = {10.1007/978-3-642-04174-7_20},
  url       = {https://mlanthology.org/ecmlpkdd/2009/rolet2009ecmlpkdd-boosting/}
}