flâneur — a map of the web's best reading

Stochastic Spectral Descent for Restricted Boltzmann Machines

proceedings.mlr.press · 776 words · saved by 1 readers

Restricted Boltzmann Machines (RBMs) are widely used as building blocks for deep learning models. Learning typically proceeds by using stochastic gradient descent, and the gradients are estimated w...

Stochastic Spectral Descent for Restricted Boltzmann Machines David Carlson, Volkan Cevher, Lawrence Carin Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics , PMLR 38:111-119, 2015. Abstract Restricted Boltzmann Machines (RBMs) are widely used as building blocks for deep learning models. Learning typically proceeds by using stochastic gradient descent, and the gradients are estimated with sampling methods. However, the gradient estimation is a computational bottleneck, so better use of the gradients will speed up the descent algorithm. To this end

Explore this link on the map →

related reading