To refer to this page use:
|Abstract:||Adaptive regularization methods pre-multiply a descent direction by a preconditioning matrix. Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive. We show how to modify full-matrix adaptive regularization in order to make it practical and effective. We also provide a novel theoretical analysis for adaptive regularization in non-convex optimization settings. The core of our algorithm, termed GGT, consists of the efficient computation of the inverse square root of a low-rank matrix. Our preliminary experiments show improved iteration-wise convergence rates across synthetic tasks and standard deep learning benchmarks, and that the more carefully-preconditioned steps sometimes lead to a better solution.|
|Citation:||Agarwal, Naman, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, and Yi Zhang. "Efficient Full-Matrix Adaptive Regularization." In Proceedings of the 36th International Conference on Machine Learning (2019): pp. 102-110.|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Proceedings of the 36th International Conference on Machine Learning|
|Version:||Final published version. Article is made available in OAR by the publisher's permission or policy.|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.