Indexed by:Journal Article

Date of Publication:2015-01-01

Journal:DISCRETE DYNAMICS IN NATURE AND SOCIETY

Included Journals:Scopus、SCIE

Volume:2015

ISSN:1026-0226

Abstract:Many generalization results in learning theory are established under the assumption that samples are independent and identically distributed (i.i.d.). However, numerous learning tasks in practical applications involve the time-dependent data. In this paper, we propose a theoretical framework to analyze the generalization performance of the empirical risk minimization (ERM) principle for sequences of time-dependent samples (TDS). In particular, we first present the generalization bound of ERM principle for TDS. By introducing some auxiliary quantities, we also give a further analysis of the generalization properties and the asymptotical behaviors of ERM principle for TDS.