Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

We present the first accelerated randomized algorithm for solving linear systems in Euclidean spaces. One essential problem of this type is the matrix inversion problem. In particular, our algorithm can be specialized to invert positive definite matrices in such a way that all iterates (approximate solutions) generated by the algorithm are positive definite matrices themselves. This opens the way for many applications in the field of optimization and machine learning. As an application of our general theory, we develop the first accelerated (deterministic and stochastic) quasi-Newton updates. Our updates lead to provably more aggressive approximations of the inverse Hessian, and lead to speed-ups over classical non-accelerated rules in numerical experiments. Experiments with empirical risk minimization show that our rules can accelerate training of machine learning models.

Published in:
Advances in Neural Information Processing Systems 31 (NIPS 2018)
Presented at:
32nd Annual Conference on Neural Information Processing Systems (NIPS), Montréal, Canada, December 2-8, 2018
Dec 02 2018
Other identifiers:

Note: The status of this file is: Anyone

 Record created 2018-11-22, last modified 2020-10-24

poster - Download fulltextPDF
main - Download fulltextPDF
Rate this document:

Rate this document:
(Not yet reviewed)