Parallelizing Spectrally Regularized Kernel Algorithms
Nicole Mücke, Gilles Blanchard · publish.UP (University of Potsdam) · 2018
We consider a distributed learning approach in supervised learning for a large class of spectral regularization methods in an reproducing kernel Hilbert space (RKHS) framework. The data set of size n is partitioned into m = O (n(alpha)), alpha infinity, depending on the smoothness assumptions on f and the intrinsic dimensionality. In spirit, the analysis relies on a classical bias/stochastic error analysis.