Interactive Structure Learning with Structural Query-by-Committee

In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks. We present a generalization of the query-by-committee active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise.

[1]  Santosh S. Vempala,et al.  The geometry of logconcave functions and sampling algorithms , 2007, Random Struct. Algorithms.

[2]  Sanjoy Dasgupta,et al.  Learning with Feature Feedback: from Theory to Practice , 2017, AISTATS.

[3]  Sanjoy Dasgupta,et al.  Learning from partial correction , 2017, ArXiv.

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

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

[6]  Shachar Lovett,et al.  Active Classification with Comparison Queries , 2017, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

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

[8]  Pranjal Awasthi,et al.  Supervised Clustering , 2010, NIPS.

[9]  Robert D. Nowak,et al.  S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification , 2015, COLT.

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

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

[12]  Claire Cardie,et al.  Clustering with Instance-Level Constraints , 2000, AAAI/IAAI.

[13]  Shai Ben-David,et al.  Clustering with Same-Cluster Queries , 2016, NIPS.

[14]  Kazuoki Azuma.  WEIGHTED SUMS OF CERTAIN DEPENDENT RANDOM VARIABLES , 1967 .

[15]  Sanjoy Dasgupta,et al.  Interactive Bayesian Hierarchical Clustering , 2016, ICML.

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

[17]  Maria-Florina Balcan,et al.  Local algorithms for interactive clustering , 2013, ICML.

[18]  Jeff A. Bilmes,et al.  Average-Case Active Learning with Costs , 2009, ALT.

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

[20]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

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

[22]  David Cohn,et al.  Active Learning , 2010, Encyclopedia of Machine Learning.

[23]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[24]  J. Lafferty,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[25]  Sanjoy Dasgupta,et al.  Lower Bounds for the Gibbs Sampler over Mixtures of Gaussians , 2014, ICML.

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

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

[28]  Shai Shalev-Shwartz,et al.  Efficient active learning of halfspaces: an aggressive approach , 2012, J. Mach. Learn. Res..

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

[30]  Maria-Florina Balcan,et al.  Clustering with Interactive Feedback , 2008, ALT.

[31]  Nicholas J. Higham,et al.  INVERSE PROBLEMS NEWSLETTER , 1991 .

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

[33]  Claudio Gentile,et al.  Learning Unknown Graphs , 2009, ALT.

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

[35]  Yichong Xu,et al.  Noise-Tolerant Interactive Learning Using Pairwise Comparisons , 2017, NIPS.

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

[37]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.