← Back to papers
2017 ICML ICML 2017

Diameter-Based Active Learning

Abstract

To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.

🧭 Keyword Pioneer — upper bound
🐣 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

Christopher Tosh , Sanjoy Dasgupta

Topics

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

Keywords

active learning concept class upper bound efficient algorithm splitting index
Download PDF

Related papers

Bottleneck Conditional Density Estimation 2017
Constrained Policy Optimization 2017
Near-Optimal Design of Experiments via Regret Minimization 2017
Input Convex Neural Networks 2017
An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation 2017