Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix

Roger B. Grosse, Ruslan Salakhutdinov. Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix. In Francis R. Bach, David M. Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015. Volume 37 of JMLR Proceedings, pages 2304-2313, JMLR.org, 2015. [doi]

Abstract

Abstract is missing.