The Common-directions Method for Regularized Empirical Risk Minimization
Po-Wei Wang, Ching-pei Lee, Chih-Jen Lin; 20(58):1−49, 2019.
State-of-the-art first- and second-order optimization methods are able to achieve either fast global linear convergence rates or quadratic convergence, but not both of them. In this work, we propose an interpolation between first- and second-order methods for regularized empirical risk minimization that exploits the problem structure to efficiently combine multiple update directions. Our method attains both optimal global linear convergence rate for first-order methods, and local quadratic convergence. Experimental results show that our method outperforms state-of-the-art first- and second-order optimization methods in terms of the number of data accesses, while is competitive in training time.
|© JMLR 2019. (edit, beta)|