Match!

Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure

Published on Feb 1, 2016in IEEE Transactions on Signal Processing5.23
· DOI :10.1109/TSP.2015.2477805
Visar Berisha11
Estimated H-index: 11
(ASU: Arizona State University),
Alan Wisler4
Estimated H-index: 4
(ASU: Arizona State University)
+ 1 AuthorsAndreas Spanias26
Estimated H-index: 26
(ASU: Arizona State University)
Abstract
Information divergence functions play a critical role in statistics and information theory. In this paper we show that a nonparametric f -divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the same distribution and for the case where there exists some mismatch between training and test distributions. We confirm these theoretical results by designing feature selection algorithms using the criteria from these bounds and by evaluating the algorithms on a series of pathological speech classification tasks.
  • References (41)
  • Citations (20)
References41
Newest
#1Visar Berisha (ASU: Arizona State University)H-Index: 11
#2Douglas Cochran (ASU: Arizona State University)H-Index: 15
May 1, 2014 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Visar Berisha (ASU: Arizona State University)H-Index: 11
#2Julie M. Liss (ASU: Arizona State University)H-Index: 24
Last.Andreas Spanias (ASU: Arizona State University)H-Index: 26
view all 5 authors...
Jan 1, 2014 in NeurIPS (Neural Information Processing Systems)
#1Kevin R. Moon (UM: University of Michigan)H-Index: 9
#2Alfred O. Hero (UM: University of Michigan)H-Index: 53
#1Kumar Sricharan (UM: University of Michigan)H-Index: 7
#2Raviv Raich (OSU: Oregon State University)H-Index: 22
Last.Alfred O. Hero (UM: University of Michigan)H-Index: 53
view all 3 authors...
#1XuanLong Nguyen (UM: University of Michigan)H-Index: 17
#2Martin J. Wainwright (University of California, Berkeley)H-Index: 67
Last.Michael I. Jordan (University of California, Berkeley)H-Index: 127
view all 3 authors...
#1Shai Ben-David (UW: University of Waterloo)H-Index: 34
#2John Blitzer (University of California, Berkeley)H-Index: 20
Last.Jennifer Wortman Vaughan (Harvard University)H-Index: 23
view all 6 authors...
Jun 18, 2009 in UAI (Uncertainty in Artificial Intelligence)
#1Yishay Mansour (TAU: Tel Aviv University)H-Index: 61
#2Mehryar Mohri (CIMS: Courant Institute of Mathematical Sciences)H-Index: 47
Last.Afshin Rostamizadeh (NYU: New York University)H-Index: 22
view all 3 authors...
Cited By20
Newest
#1Yuanhua Fu (University of Electronic Science and Technology of China)
#2Zhiming He (University of Electronic Science and Technology of China)
May 1, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Salimeh Yasaei Sekeh (UM: University of Michigan)H-Index: 5
#2Alfred O. Hero (UM: University of Michigan)H-Index: 53
#1Fredrik D. Johansson (MIT: Massachusetts Institute of Technology)H-Index: 8
#2David Sontag (MIT: Massachusetts Institute of Technology)H-Index: 27
Last.Rajesh Ranganath (NYU: New York University)H-Index: 1
view all 3 authors...
#1Sally Ghanem (NCSU: North Carolina State University)
#2Hamid Krim (NCSU: North Carolina State University)H-Index: 25
Last.Wesam Sakla (LLNL: Lawrence Livermore National Laboratory)H-Index: 2
view all 4 authors...
Last.Mahesh K. Banavar (Clarkson University)H-Index: 12
view all 5 authors...
#1Salimeh Yasaei Sekeh (UM: University of Michigan)H-Index: 5
#2Brandon Oselio (UM: University of Michigan)H-Index: 3
Last.Alfred O. Hero (UM: University of Michigan)H-Index: 53
view all 3 authors...
View next paperNonparametric Bayes error estimation for HRR target identification