← Back to papers
2010 JMLR JMLR 2010

Rademacher Complexities and Bounding the Excess Risk in Active Learning

Abstract

Sequential algorithms of active learning based on the estimation of the level sets of the empirical risk are discussed in the paper. Localized Rademacher complexities are used in the algorithms to estimate the sample sizes needed to achieve the required accuracy of learning in an adaptive way. Probabilistic bounds on the number of active examples have been proved and several applications to binary classification problems are considered. [abs] [ pdf ][ bib ] © JMLR 2010. (edit, beta)

🐣 Hot Topic Early Bird — active learning
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Vladimir Koltchinskii

Topics

Machine Learning > Learning Types > Active Learning Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning

Keywords

active learning binary classification sample complexity rademacher complexity excess risk bound empirical risk
Download PDF

Related papers

A Fast Hybrid Algorithm for Large-Scale -Regularized Logistic Regression 2010
Model-based Boosting 2.0 2010
On Learning with Integral Operators 2010
Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data 2010
Hilbert Space Embeddings and Metrics on Probability Measures 2010