UPAL: Unbiased Pool Based Active Learning

Abstract

In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of linear classifiers and the squared loss we show that UPAL is equivalent to an exponentially weighted average forecaster. Exploiting some recent results regarding the spectra of random matrices allows us to establish consistency of UPAL when the true hypothesis is a linear hypothesis. Empirical comparison with an active learner implementation in Vowpal Wabbit, and a previously proposed pool based active learner implementation show good empirical performance and better scalability.

20 pages, 4 figures, 2 tables, a few minor typos were corrected

References in corpus (2)

• UPAL: Unbiased Pool Based Active Learning
• Dimension-free tail inequalities for sums of random matrices

Cited by in corpus (12)

• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• On Statistical Bias In Active Learning: How and When To Fix It
• UPAL: Unbiased Pool Based Active Learning
• Active Testing: Sample-Efficient Model Evaluation
• Building Bridges: Viewing Active Learning from the Multi-Armed Bandit Lens
• Active Regression by Stratification
• Noisy Batch Active Learning with Deterministic Annealing
• Active Hybrid Classification
• Importance of Self-Consistency in Active Learning for Semantic Segmentation
• Analyzing Data Selection Techniques with Tools from the Theory of Information Losses
• Selective Harvesting over Networks