Editor-in-Chief: Stumpf, Michael P.H.
Editorial Board Member: Beaumont, Mark / Binder, Harald / Gupta, Mayetri / Hubbard, Alan E. / Husmeier, Dirk / Ji, Hongkai / Keles, Sunduz / Kerr, Kathleen / Lazzeroni, Laura / Lin, Shili / Ma, Ping / Marjoram, Paul / Mertens, Bart / Nerman, Olle / G. Petretto, Enrico / Plagnol, Vincent / Purdom, Elizabeth / Robin, Stéphane / Rzhetsky, Andrey / Sanguinetti, Guido / van der Laan, Mark J. / von Haeseler, Arndt / Weeks, Daniel E. / Wiuf, Carsten / Zhao, Hongyu
1 Issue per year
IMPACT FACTOR 2011: 1.517
5-year IMPACT FACTOR: 1.704
Rank 27 out of 116 in category Statistics & Probability in the 2011 Thomson Reuters Journal Citation Report/Science Edition
Volume 12 (2013)
Volume 11 (2012)
Volume 10 (2011)
Volume 9 (2010)
Volume 8 (2009)
Volume 6 (2007)
Volume 5 (2006)
Volume 4 (2005)
Volume 3 (2004)
Volume 2 (2003)
Volume 1 (2002)
Most Downloaded Articles
- A General Framework for Weighted Gene Co-Expression Network Analysis by Zhang, Bin and Horvath, Steve
- Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments by Smyth, Gordon K
- Detecting Differential Expression in RNA-sequence Data Using Quasi-likelihood with Shrunken Dispersion Estimates by Lund, Steven P./ Nettleton, Dan/ McCarthy, Davis J. and Smyth, Gordon K.
- Adjusting for Spurious Gene-by-Environment Interaction Using Case-Parent Triads by Shin, Ji-Hyung/ Infante-Rivard, Claire/ Graham, Jinko and McNeney, Brad
- A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics by Schäfer, Juliane and Strimmer, Korbinian
A Calibrated Multiclass Extension of AdaBoost
1U.S. Food and Drug Administration
Citation Information: Statistical Applications in Genetics and Molecular Biology. Volume 10, Issue 1, Pages 1–24, ISSN (Online) 1544-6115, DOI: 10.2202/1544-6115.1731, November 2011
- Published Online:
AdaBoost is a popular and successful data mining technique for binary classification. However, there is no universally agreed upon extension of the method for problems with more than two classes. Most multiclass generalizations simply reduce the problem to a series of binary classification problems. The statistical interpretation of AdaBoost is that it operates through loss-based estimation: by using an exponential loss function as a surrogate for misclassification loss, it sequentially minimizes empirical risk through fitting a base classifier to iteratively reweighted training data. While there are several extensions using loss-based estimation with multiclass base classifiers, these use multiclass versions of the exponential loss that are not classification calibrated: unless restrictions are placed on conditional class probabilities, it becomes possible to have optimal surrogate risk but poor misclassification risk. In this work, we introduce a new AdaBoost extension called AdaBoost.
SL that does not reduce the problem into binary subproblems and that uses a classification-calibrated multiclass exponential loss function. Numerical experiments show the algorithm performs well on benchmark datasets.