Work

Solving Ridge Regression using Sketched Preconditioned SVRG

Year: 2016

Type: preprint

Abstract: We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1602.02350

Authors: Gonen, Alon, Orabona, Francesco, Shalev-Shwartz, Shai

Institutions: Hebrew University of Jerusalem, Yahoo (United States)

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2270051965

Cites: 12

Cited by: 27

Related to: 20