Greedy Active Learning Algorithm for Logistic Regression Models

2018/02/01 by Hsiang-Ling Hsu, Hsu, Hsiang-Ling, Yuan-Chin Ivan Chang +3
Mathematics · #FOS: Computer and information sciences #Machine Learning (stat.ML) #stat.ML

paper · pdf · doi:10.48550/arxiv.1802.00243

arxiv created 2018/02/01 · arxiv updated 2018/02/02

Abstract

We study a logistic model-based active learning procedure for binary classification problems, in which we adopt a batch subject selection strategy with a modified sequential experimental design method. Moreover, accompanying the proposed subject selection scheme, we simultaneously conduct a greedy variable selection procedure such that we can update the classification model with all labeled training subjects. The proposed algorithm repeatedly performs both subject and variable selection steps until a prefixed stopping criterion is reached. Our numerical results show that the proposed procedure has competitive performance, with smaller training size and a more compact model, comparing with that of the classifier trained with all variables and a full data set. We also apply the proposed procedure to a well-known wave data set (Breiman et al., 1984) to confirm the performance of our method.

Related

• Active learning for binary classification with variable selection
• Near-Polynomially Competitive Active Logistic Regression
• Learning to Rank for Active Learning via Multi-Task Bilevel Optimization
• The Knowledge Gradient with Logistic Belief Models for Binary Classification
• Active Model Selection