We develop a unified approach for classification and regression support vector machines for when the responses are subject to right censoring. We provide finite sample bounds on the generalization error of the algorithm, prove risk consistency for a wide class of probability measures, and study the associated learning rates. We apply the general methodology to estimation of the (truncated) mean, median, quantiles, and for classification problems. We present a simulation study that demonstrates the performance of the proposed approach.
Bibliographical noteFunding Information:
The authors thank Danyu Lin for many helpful discussions and suggestions. The first author was funded in part by a Gillings Innovation Laboratory (GIL) award at the UNC Gillings School of Global Public Health and by Norsk SykepleierforbundNSF grant DMS-1407732. The second author was funded in part by NCINational Cancer Institute grant CA142538 and by NSFNorsk Sykepleierforbund grant DMS-1407732.
© 2017, Institute of Mathematical Statistics. All rights reserved.
- Generalization error
- Misspecification models
- Right censored data
- Support vector regression
- Universal consistency
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty