Title :
Law of the iterated logarithm for a constant-gain linear stochastic gradient algorithm
Author :
Joslin, Jeff A. ; Heunis, Andrew J.
Author_Institution :
Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
Abstract :
We characterize the finite-horizon limiting properties of a constant-gain linear stochastic gradient algorithm, as the adaptation gain tends to zero, in the form of a functional law of the iterated logarithm
Keywords :
Gaussian processes; Markov processes; gradient methods; iterative methods; probability; Gauss-Markov process; interpolation; iterated logarithm; probability; stochastic gradient algorithm; Differential equations; Gaussian processes; Interpolation; Joining processes; Random sequences; Random variables; Stochastic processes;
Conference_Titel :
Decision and Control, 2001. Proceedings of the 40th IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-7061-9
DOI :
10.1109/.2001.981010
