ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Convex Calibration Dimension for Multiclass Loss Matrices

Ramaswamy, Harish G and Agarwal, Shivani (2016) Convex Calibration Dimension for Multiclass Loss Matrices. In: JOURNAL OF MACHINE LEARNING RESEARCH, 17 .

[img] PDF
Jou_Mac_Lea_Res_17_2016.pdf - Published Version

Download (759kB)
Official URL: http://www.jmlr.org/papers/volume17/14-316/14-316....


We study consistency properties of surrogate loss functions for general multiclass learning problems, de fined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be calibrated with respect to a loss matrix in this setting. We then introduce the notion of convex calibration dimension of a multiclass loss matrix, which measures the smallest `size' of a prediction space in which it is possible to design a convex surrogate that is calibrated with respect to the loss matrix. We derive both upper and lower bounds on this quantity, and use these results to analyze various loss matrices. In particular, we apply our framework to study various subset ranking losses, and use the convex calibration dimension as a tool to show both the existence and non-existence of various types of convex calibrated surrogates for these losses. Our results strengthen recent results of Duchi et al. (2010) and Calauzenes et al. (2012) on the non-existence of certain types of convex calibrated surrogates in subset ranking. We anticipate the convex calibration dimension may prove to be a useful tool in the study and design of surrogate losses for general multiclass learning problems.

Item Type: Journal Article
Additional Information: Copy right for this article belongs to the MICROTOME PUBL, 31 GIBBS ST, BROOKLINE, MA 02446 USA
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Depositing User: Id for Latest eprints
Date Deposited: 09 Feb 2017 07:05
Last Modified: 09 Feb 2017 07:05
URI: http://eprints.iisc.ac.in/id/eprint/56231

Actions (login required)

View Item View Item