Randomized Block Cubic Newton Method
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:12901298, 2018.
Abstract
We study the problem of minimizing the sum of three convex functions: a differentiable, twicedifferentiable and a nonsmooth term in a high dimensional setting. To this effect we propose and analyze a randomized block cubic Newton (RBCN) method, which in each iteration builds a model of the objective function formed as the sum of the natural models of its three components: a linear model with a quadratic regularizer for the differentiable term, a quadratic model with a cubic regularizer for the twice differentiable term, and perfect (proximal) model for the nonsmooth term. Our method in each iteration minimizes the model over a random subset of blocks of the search variable. RBCN is the first algorithm with these properties, generalizing several existing methods, matching the best known bounds in all special cases. We establish ${\cal O}(1/\epsilon)$, ${\cal O}(1/\sqrt{\epsilon})$ and ${\cal O}(\log (1/\epsilon))$ rates under different assumptions on the component functions. Lastly, we show numerically that our method outperforms the stateoftheart on a variety of machine learning problems, including cubically regularized leastsquares, logistic regression with constraints, and Poisson regression.
Related Material


