In the paper,we investigate the complete convergence and complete moment convergence for the maximal partial sum of martingale diference sequence.Especially,we get the Baum–Katz-type Theorem and Hsu–Robbins-type The...In the paper,we investigate the complete convergence and complete moment convergence for the maximal partial sum of martingale diference sequence.Especially,we get the Baum–Katz-type Theorem and Hsu–Robbins-type Theorem for martingale diference sequence.As an application,a strong law of large numbers for martingale diference sequence is obtained.展开更多
By using the stochastic martingale theory, convergence properties of stochastic gradient (SG) identification algorithms are studied under weak conditions. The analysis indicates that the parameter estimates by the S...By using the stochastic martingale theory, convergence properties of stochastic gradient (SG) identification algorithms are studied under weak conditions. The analysis indicates that the parameter estimates by the SG algorithms consistently converge to the true parameters, as long as the information vector is persistently exciting (i.e., the data product moment matrix has a bounded condition number) and that the process noises are zero mean and uncorrelated. These results remove the strict assumptions, made in existing references, that the noise variances and high-order moments exist, and the processes are stationary and ergodic and the strong persis- tent excitation condition holds. This contribution greatly relaxes the convergence conditions of stochastic gradient algorithms. The simulation results with bounded and unbounded noise variances confirm the convergence conclusions proposed.展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.11201001,11171001,11126176 and 11226207)Natural Science Foundation of Anhui Province(Grant Nos.1208085QA03 and 1308085QA03)+2 种基金Applied Teaching Model Curriculum of Anhui University(Grant No.XJYYXKC04)Students Innovative Training Project of Anhui University(Grant No.201310357004)Doctoral Research Start-up Funds Projects of Anhui University and the Students Science Research Training Program of Anhui University(Grant No.KYXL2012007)
文摘In the paper,we investigate the complete convergence and complete moment convergence for the maximal partial sum of martingale diference sequence.Especially,we get the Baum–Katz-type Theorem and Hsu–Robbins-type Theorem for martingale diference sequence.As an application,a strong law of large numbers for martingale diference sequence is obtained.
基金Supported by the National Natural Science Foundation of China (Grant Nos. 60574051 and 60674092) the Natural Science Foundation of Jiangsu Province, China (Grant No. BK2007017) and by Program for Innovative Research Team of Jiangnan University
文摘By using the stochastic martingale theory, convergence properties of stochastic gradient (SG) identification algorithms are studied under weak conditions. The analysis indicates that the parameter estimates by the SG algorithms consistently converge to the true parameters, as long as the information vector is persistently exciting (i.e., the data product moment matrix has a bounded condition number) and that the process noises are zero mean and uncorrelated. These results remove the strict assumptions, made in existing references, that the noise variances and high-order moments exist, and the processes are stationary and ergodic and the strong persis- tent excitation condition holds. This contribution greatly relaxes the convergence conditions of stochastic gradient algorithms. The simulation results with bounded and unbounded noise variances confirm the convergence conclusions proposed.