A decision-theoretic generalization of on-line learning and an application to boosting. In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone-Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in $bfR^n$. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.

References in zbMATH (referenced in 341 articles , 1 standard article )

Showing results 1 to 20 of 341.
Sorted by year (citations)

1 2 3 ... 16 17 18 next

  1. Alon, Noga; Cesa-Bianchi, Nicolò; Gentile, Claudio; Mannor, Shie; Mansour, Yishay; Shamir, Ohad: Nonstochastic multi-armed bandits with graph-structured feedback (2017)
  2. Fan, Zhihui; Li, Zheqing; Li, Peiyu; Wang, Hui: Motion segmentation based on dual interrelated models (2017)
  3. Feige, Uriel; Koren, Tomer; Tennenholtz, Moshe: Chasing ghosts: competing with stateful policies (2017)
  4. Gotoh, Jun-ya; Uryasev, Stan: Support vector machines based on convex risk functions and general norms (2017)
  5. Gutfreund, Dan; Kontorovich, Aryeh; Levy, Ran; Rosen-Zvi, Michal: Boosting conditional probability estimators (2017)
  6. Proença, Hugo; Neves, João C.: Fusing vantage point trees and linear discriminants for fast feature classification (2017)
  7. Srinivasan, Ashwin; Bain, Michael: An empirical study of on-line models for relational data streams (2017)
  8. Adamskiy, Dmitry; Koolen, Wouter M.; Chernov, Alexey; Vovk, Vladimir: A closer look at adaptive regret (2016)
  9. Ali, Farman; Hayat, Maqsood: Machine learning approaches for discrimination of extracellular matrix proteins using hybrid feature space (2016)
  10. Buchbinder, Niv; Chen, Shahar; Naor, Joseph (Seffi); Shamir, Ohad: Unified algorithms for online learning and competitive analysis (2016)
  11. Gadat, Sébastien; Klein, Thierry; Marteau, Clément: Classification in general finite dimensional spaces with the $k$-nearest neighbor rule (2016)
  12. Geurts, Pierre; Wehenkel, Louis: Comments on: “A random forest guided tour” (2016)
  13. Lecué, Guillaume; Mendelson, Shahar: Performance of empirical risk minimization in linear aggregation (2016)
  14. Manukyan, Artür; Ceyhan, Elvan: Classification of imbalanced data with a geometric digraph family (2016)
  15. Mohri, Mehryar; Yang, Scott: Structural online learning (2016)
  16. Moran, Shay; Warmuth, Manfred K.: Labeled compression schemes for extremal classes (2016)
  17. Nakazono, Takumi; Moridomi, Ken-ichiro; Hatano, Kohei; Takimoto, Eiji: A combinatorial metrical task system problem under the uniform metric (2016)
  18. Neu, Gergely; Bartók, Gábor: Importance weighting without importance weights: an efficient algorithm for combinatorial semi-bandits (2016)
  19. Nie, Jiazhong; Kotlowski, Wojciech; Warmuth, Manfred K.: Online PCA with optimal regret (2016)
  20. Nikolaou, Nikolaos; Edakunni, Narayanan; Kull, Meelis; Flach, Peter; Brown, Gavin: Cost-sensitive boosting algorithms: do we really need them? (2016)

1 2 3 ... 16 17 18 next