Conjugate Directions for Stochastic Gradient Descent [chapter]

Nicol N. Schraudolph, Thore Graepel
2002 Lecture Notes in Computer Science  
The method of conjugate gradients provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to stochastic approximation of the gradient. Here we explore ideas from conjugate gradient in the stochastic (online) setting, using fast Hessian-gradient products to set up low-dimensional Krylov subspaces within individual mini-batches. In our benchmark experiments the resulting online learning algorithms converge
more » ... of magnitude faster than ordinary stochastic gradient descent.
doi:10.1007/3-540-46084-5_218 fatcat:mye3y4evavggdekufwafdd53ba