Boosting, Voting Classifiers and Randomized Sample Compression Schemes
da Cunha, Arthur, Larsen, Kasper Green, Ritzert, Martin
–arXiv.org Artificial Intelligence
In boosting, we aim to leverage multiple weak learners to produce a strong learner. At the center of this paradigm lies the concept of building the strong learner as a voting classifier, which outputs a weighted majority vote of the weak learners. While many successful boosting algorithms, such as the iconic AdaBoost, produce voting classifiers, their theoretical performance has long remained sub-optimal: the best known bounds on the number of training examples necessary for a voting classifier to obtain a given accuracy has so far always contained at least two logarithmic factors above what is known to be achievable by general weak-to-strong learners. In this work, we break this barrier by proposing a randomized boosting algorithm that outputs voting classifiers whose generalization error contains a single logarithmic dependency on the sample size. We obtain this result by building a general framework that extends sample compression methods to support randomized learning algorithms based on sub-sampling.
arXiv.org Artificial Intelligence
Feb-5-2024
- Country:
- Europe
- Austria (0.14)
- Germany > Lower Saxony
- Gottingen (0.14)
- Europe
- Genre:
- Research Report (0.50)
- Technology: