Adaptive Region-Based Active Learning

We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels. We prove theoretical guarantees for both the generalization error and the label complexity of our algorithm, and analyze the number of regions defined by the algorithm under some mild assumptions. We also report the results of an extensive suite of experiments on several real-world datasets demonstrating substantial empirical benefits over existing single-region and non-adaptive region-based active learning baselines.

[1]  Mehryar Mohri,et al.  Structured Prediction Theory Based on Factor Graph Complexity , 2016, NIPS.

[2]  Andreas Krause,et al.  Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization , 2010, COLT 2010.

[3]  Sanjoy Dasgupta,et al.  Hierarchical sampling for active learning , 2008, ICML '08.

[4]  Claudio Gentile,et al.  Active Learning with Disagreement Graphs , 2019, ICML.

[5]  Sanjoy Dasgupta,et al.  A General Agnostic Active Learning Algorithm , 2007, ISAIM.

[6]  Robert D. Nowak,et al.  The Geometry of Generalized Binary Search , 2009, IEEE Transactions on Information Theory.

[7]  John Langford,et al.  Importance weighted active learning , 2008, ICML '09.

[8]  Liu Yang,et al.  Minimax Analysis of Active Learning , 2014, J. Mach. Learn. Res..

[9]  Robert D. Nowak,et al.  Minimax Bounds for Active Learning , 2007, IEEE Transactions on Information Theory.

[10]  Sanjoy Dasgupta,et al.  Diameter-Based Active Learning , 2017, ICML.

[11]  Sanjoy Dasgupta,et al.  Analysis of a greedy active learning strategy , 2004, NIPS.

[12]  Koby Crammer,et al.  Adaptive regularization of weight vectors , 2009, Machine Learning.

[13]  John Langford,et al.  Agnostic active learning , 2006, J. Comput. Syst. Sci..

[14]  Sanjoy Dasgupta,et al.  Two faces of active learning , 2011, Theor. Comput. Sci..

[15]  Steve Hanneke,et al.  A bound on the label complexity of agnostic active learning , 2007, ICML '07.

[16]  Sanjoy Dasgupta,et al.  Coarse sample complexity bounds for active learning , 2005, NIPS.

[17]  Chicheng Zhang,et al.  Efficient active learning of sparse halfspaces , 2018, COLT.

[18]  Maria-Florina Balcan,et al.  Margin Based Active Learning , 2007, COLT.

[19]  Kamalika Chaudhuri,et al.  Beyond Disagreement-Based Agnostic Active Learning , 2014, NIPS.

[20]  Maria-Florina Balcan,et al.  Active and passive learning of linear separators under log-concave distributions , 2012, COLT.

[21]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[22]  Andreas Krause,et al.  Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization , 2010, J. Artif. Intell. Res..

[23]  Percy Liang,et al.  On the Relationship between Data Efficiency and Error for Uncertainty Sampling , 2018, ICML.

[24]  Vladimir Koltchinskii,et al.  Rademacher Complexities and Bounding the Excess Risk in Active Learning , 2010, J. Mach. Learn. Res..

[25]  John Langford,et al.  Agnostic Active Learning Without Constraints , 2010, NIPS.

[26]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[27]  Shai Ben-David,et al.  Hierarchical Label Queries with Data-Dependent Partitions , 2015, COLT.

[28]  Steve Hanneke,et al.  Theory of Disagreement-Based Active Learning , 2014, Found. Trends Mach. Learn..

[29]  Claudio Gentile,et al.  Region-Based Active Learning , 2019, AISTATS.

[30]  John Langford,et al.  Efficient and Parsimonious Agnostic Active Learning , 2015, NIPS.

[31]  Adam Tauman Kalai,et al.  Analysis of Perceptron-Based Active Learning , 2009, COLT.

[32]  Maria-Florina Balcan,et al.  Efficient Learning of Linear Separators under Bounded Noise , 2015, COLT.