Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
JOURNAL OF MACHINE LEARNING RESEARCH, pp. 3608-3616, 2018.
We address the statistical and optimization impacts of the classical sketch and Hessian sketch used to approximately solve the Matrix Ridge Regression (MRR) problem. Prior research has quantified the effects of classical sketch on the strictly simpler least squares regression (LSR) problem. We establish that classical sketch has a similar...更多
下载 PDF 全文