Minimax bounds for active learning

Minimax bounds for active learning (2007)

Cached

Download Links

[www.ece.wisc.edu]
[nowak.ece.wisc.edu]

Other Repositories/Bibliography

DBLP

by Rui M. Castro , Robert D. Nowak

Venue:	In COLT
Citations:	31 - 3 self

BibTeX

@INPROCEEDINGS{Castro07minimaxbounds,
    author = {Rui M. Castro and Robert D. Nowak},
    title = {Minimax bounds for active learning},
    booktitle = {In COLT},
    year = {2007},
    pages = {151--156},
    publisher = {Verlag}
}

Bookmark

OpenURL

Abstract

Abstract. This paper aims to shed light on achievable limits in active learning. Using minimax analysis techniques, we study the achievable rates of classification error convergence for broad classes of distributions characterized by decision boundary regularity and noise conditions. The results clearly indicate the conditions under which one can expect significant gains through active learning. Furthermore we show that the learning rates derived are tight for “boundary fragment ” classes in ddimensional feature spaces when the feature marginal density is bounded from above and below. 1

Citations

402	Active learning with statistical models - Cohn, Ghahramani, et al. - 1996
256	Selective sampling using the query by committee algorithm, Machine Learning 28 - Freund, Seung, et al. - 1997
236	Information-Based Objective Functions for Active Data - MacKay - 1992
100	Optimal aggregation of classifiers in statistical learning - Tsybakov
80	Agnostic active learning - Balcan, Beygelzimer, et al. - 2006
67	Coarse sample complexity bounds for active learning - Dasgupta - 2005
51	Analysis of perceptron-based active learning - Dasgupta, Kalai, et al. - 2009
50	Analysis of a greedy active learning strategy - Dasgupta - 2004
42	Introduction à l’estimation non-paramétrique - Tsybakov - 2004
30	Active learning in the non-realizable case - Kääriäinen - 2006
26	Hierarchical testing designs for pattern recognition - Blanchard, Geman - 2005
26	On nonparametric estimation of density level sets - Tsybakov - 1997
25	Faster rates in regression via active learning - Castro, Willett, et al. - 2005
22	Learning probabilistic linear-threshold classifiers via selective sampling - Cesa-Bianchi, Conconi, et al. - 2003
17	An interval estimation problem for controlled observations - Burnashev, Zigangirov - 1974
10	Sequential methods for design-adaptive estimation of discontinuities in regression curves and surfaces - Hall, Molchanov - 2003
9	Nonparametric estimation of regression level sets - Cavalier - 1997
8	On minimax rates of convergence in image models under sequential design - Korostelev - 1999
6	Active learning for identifying function threshold boundaries - Bryan, Schneider, et al. - 2005
6	Upper and lower bounds for active learning - Castro, Nowak - 2006
6	The error in polynomial tensor-product, and in Chung-Yao, interpolation - Boor - 1997
4	Sequential recovery of analytic periodic edges in the binary image models - Golubev, Levit - 2003
4	Rates of convergence for the supnorm risk in image models under sequential designs - Korostelev, Kim - 2000