← Back to papers
2012 JMLR JMLR 2012

Plug-in Approach to Active Learning

Abstract

We present a new active learning algorithm based on nonparametric estimators of the regression function. Our investigation provides probabilistic bounds for the rates of convergence of the generalization error achievable by proposed method over a broad class of underlying distributions. We also prove minimax lower bounds which show that the obtained rates are almost tight. [abs] [ pdf ][ bib ] © JMLR 2012. (edit, beta)

🧭 Keyword Pioneer — regression function
🐣 Hot Topic Early Bird — generalization error
🐝 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

Stanislav Minsker

Topics

Machine Learning > Learning Types > Active Learning

Keywords

active learning nonparametric estimation generalization error minimax lower bound regression function
Download PDF

Related papers

An Active Learning Algorithm for Ranking from Pairwise Preferences with an Almost Optimal Query Complexity 2012
Eliminating Spammers and Ranking Annotators for Crowdsourced Labeling Tasks 2012
GPLP: A Local and Parallel Computation Toolbox for Gaussian Process Regression 2012
Query Strategies for Evading Convex-Inducing Classifiers 2012
A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction: Insights and New Models 2012