A New Convergent Algorithm for Online Empirical Risk Minimization
作者单位:Key Lab.of Systems and ControlInstitute of Systems ScienceAMSSCAS
会议名称:《第36届中国控制会议》
会议日期:2017年
学科分类:12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
关 键 词:ERM random search convergent gradient descent machine learning
摘 要:The generalization ability of learning algorithms is the focus of machine learning research,where the empirical risk minimization(ERM) plays an important role when the population distribution of observations is *** of the previous results are mainly based on computational learning theory,which is interested in how many samples are needed to make sure the estimated expected risk satisfies a given accuracy with high *** this paper,we will propose a new algorithm by combining the advantages of both random search and gradient descent algorithms,and show that given an accuracy level of the estimated expected risk,we can generate a hypothesis by our algorithm to guarantee the accuracy with probability 1,and our algorithm will converge in finite *** addition,we will relax the conventional independently and identically distributed(i.i.d.)assumption on the observations to a kind of weakly dependent *** will also provide some simulations to demonstrate our algorithm’s advantages over either random search or gradient descent algorithms.