点击次数：

论文类型：期刊论文

发表时间：2015-01-01

发表刊物：DISCRETE DYNAMICS IN NATURE AND SOCIETY

收录刊物：SCIE、Scopus

卷号：2015

ISSN号：1026-0226

摘要：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.