We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points. Armed with this capability, we conduct a thorough comparison between the full kernel, the Nyström method, and random features on three large classification tasks from various domains. Our results suggest that the Nyström method generally achieves...

Coordinate descent methods have considerable impact in global optimization because (or, at least, almost global) minimization is affordable for low-dimensional problems. with high-order regularized models smooth nonconvex box-constrained are introduced this work. High-order stationarity asymptotic convergence and first-order worst-case evaluation complexity bounds established. The computer work...

Several works have shown linear speedup is achieved by an asynchronous parallel implementation of stochastic coordinate descent so long as there not too much parallelism. More specifically, it known that if all updates are similar duration, then possible with up to $\Theta(L_{\max}\sqrt n/L_{\overline{{res}}})$ processors, where $L_{\max}$ and $L_{\overline{{res}}}$ suitable Lipschitz parameter...