Search Machine Learning Repository:
Finito: A faster, permutable incremental gradient method for big data problems
Authors: Aaron Defazio, Justin Domke and Tiberio Caetano
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work we introduce a new method in this class with a theoretical convergence rate four times faster than existing methods, for sums with sufficiently many terms. This method is also amendable to a sampling without replacement scheme that in practice gives further speed-ups. We give empirical results showing state of the art performance.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).