Sciweavers

SIAMCO
2000
104views more  SIAMCO 2000»
13 years 11 months ago
Law of the Iterated Logarithm for a Constant-Gain Linear Stochastic Gradient Algorithm
We study almost-sure limiting properties, taken as 0, of the finite horizon sequence of random estimates { 0, 1, 2, . . . , T/ } for the linear stochastic gradient algorithm n+1 ...
J. A. Joslin, A. J. Heunis