Efficient and Parsimonious Agnostic Active Learning

2015/06/29 by Tzu-Kuo Huang, Huang, Tzu-Kuo, Alekh Agarwal +7 · 1 citation
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1506.08669

arxiv created 2016/01/07 · arxiv updated 2016/01/08

Abstract

We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise. 2) It is efficiently implementable with an ERM oracle. 3) It is more aggressive than all previous approaches satisfying 1 and 2. To do this we create an algorithm based on a newly defined optimization problem and analyze it. We also conduct the first experimental analysis of all efficient agnostic active learning algorithms, evaluating their strengths and weaknesses in different settings.

Cited by

• Towards Fundamental Limits for Active Multi-distribution Learning

Related

• Improved Algorithms for Neural Active Learning
• Neural Active Learning with Performance Guarantees
• Neural Active Learning Beyond Bandits
• Streaming Active Learning with Deep Neural Networks
• Active Labeling: Streaming Stochastic Gradients