no code implementations • ICLR 2021 • Huang Fang, Zhenan Fan, Michael Friedlander
We prove that SSGD converges, respectively, with rates $O(1/\epsilon)$ and $O(\log(1/\epsilon))$ for convex and strongly-convex objectives when interpolation holds.
no code implementations • NeurIPS 2016 • Gabriel Goh, Andrew Cotter, Maya Gupta, Michael Friedlander
The goal of minimizing misclassification error on a training set is often just one of several real-world goals that might be defined on different datasets.
no code implementations • 1 Jun 2015 • Julie Nutini, Mark Schmidt, Issam H. Laradji, Michael Friedlander, Hoyt Koepke
There has been significant recent work on the theory and application of randomized coordinate descent algorithms, beginning with the work of Nesterov [SIAM J.