Lin, JunhongCevher, Volkan2018-03-102018-03-102018-03-102018-03-11https://infoscience.epfl.ch/handle/20.500.14299/1454141803.04371We investigate regularized algorithms combining with projection for least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space. We prove convergence results with respect to variants of norms, under a capacity assumption on the hypothesis space and a regularity condition on the target function. As a result, we obtain optimal rates for regularized algorithms with randomized sketches, provided that the sketch dimension is proportional to the effective dimension up to a logarithmic factor. As a byproduct, we obtain similar results for Nystr\"{o}m regularized algorithms. Our results are the first ones with optimal, distribution-dependent rates that do not have any saturation effect for sketched/Nystr\"{o}m regularized algorithms, considering both the attainable and non-attainable cases.Regularized AlgorithmsKernel MethodsProjectionRandomized SketchingNystrom SubsamplingOptimal Ratesml-aitext::conference output::conference proceedings::conference paper