2015 OptimalandAdaptiveAlgorithmsfor
- (Beygelzimer et al., 2015) ⇒ Alina Beygelzimer, Satyen Kale, and Haipeng Luo. (2015). “Optimal and Adaptive Algorithms for Online Boosting.” In: Proceedings of ICML-2015.
Subject Headings: Online Learning Algorithm, Boosted Learning Algorithm.
Notes
Cited By
Quotes
Abstract
We study online boosting, the task of converting any weak online learner into a strong online learner. Based on a novel and natural definition of weak online learnability, we develop two online boosting algorithms. The first algorithm is an online version of boost-by-majority. By proving a matching lower bound, we show that this algorithm is essentially optimal in terms of the number of weak learners and the sample complexity needed to achieve a specified accuracy. This optimal algorithm is not adaptive however. Using tools from online loss minimization, we derive an adaptive online boosting algorithm that is also parameter-free, but not optimal. Both algorithms work with base learners that can handle example importance weights directly, as well as by rejection sampling examples with probability defined by the booster. Results are complemented with an extensive experimental study.
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2015 OptimalandAdaptiveAlgorithmsfor | Alina Beygelzimer Satyen Kale Haipeng Luo | Optimal and Adaptive Algorithms for Online Boosting |