An Adaptive Strategy for Active Learning with Smooth Decision Boundary

We present the first adaptive strategy for active learning in the setting of classification with smooth decision boundary. The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro and Nowak (2007), which first established (active learning) rates for this setting. While some recent advances on this problem establish adaptive rates in the case of univariate data, adaptivity in the more practical setting of multivariate data has so far remained elusive. Combining insights from various recent works, we show that, for the multivariate case, a careful reduction to univariate-adaptive strategies yield near-optimal rates without prior knowledge of distributional parameters.

[1]  Steve Hanneke.  Rates of convergence in active learning , 2011, 1103.1790.

[2]  Vianney Perchet,et al.  The multi-armed bandit problem with covariates , 2011, ArXiv.

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

[4]  Alexandre B. Tsybakov,et al.  Introduction to Nonparametric Estimation , 2008, Springer series in statistics.

[5]  Alexandra Carpentier,et al.  Adaptivity to Noise Parameters in Nonparametric Active Learning , 2017, COLT.

[6]  Aurélien Garivier,et al.  On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models , 2014, J. Mach. Learn. Res..

[7]  Rui M. Castro,et al.  Active Learning and Adaptive Sampling for Non-Parametric Inference , 2007 .

[8]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[9]  H. Sebastian Seung,et al.  Information, Prediction, and Query by Committee , 1992, NIPS.

[10]  A. Tsybakov,et al.  Optimal aggregation of classifiers in statistical learning , 2003 .

[11]  Stanislav Minsker,et al.  Plug-in Approach to Active Learning , 2011, J. Mach. Learn. Res..

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

[13]  Eli Upfal,et al.  Bandits and Experts in Metric Spaces , 2013, J. ACM.

[14]  Steve Hanneke,et al.  Adaptive Rates of Convergence in Active Learning , 2009, COLT.

[15]  Aurélien Garivier,et al.  The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond , 2011, COLT.

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

[17]  Aarti Singh,et al.  Algorithmic Connections between Active Learning and Stochastic Convex Optimization , 2013, ALT.

[18]  Liwei Wang,et al.  Smoothness, Disagreement Coefficient, and the Label Complexity of Agnostic Active Learning , 2011, J. Mach. Learn. Res..

[19]  Rémi Munos,et al.  Optimistic Optimization of Deterministic Functions , 2011, NIPS 2011.

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

[21]  V. Spokoiny,et al.  Optimal pointwise adaptive methods in nonparametric estimation , 1997 .

[22]  Tara Javidi,et al.  Active Learning from Imperfect Labelers , 2016, NIPS.