TY - JOUR
T1 - Sketching structured matrices for faster nonlinear regression
AU - Avron, Haim
AU - Sindhwani, Vikas
AU - Woodruff, David P.
PY - 2013
Y1 - 2013
N2 - Motivated by the desire to extend fast randomized techniques to nonlinear lp regression, we consider a class of structured regression problems. These problems involve Vandermonde matrices which arise naturally in various statistical modeling settings, including classical polynomial fitting problems, additive models and approximations to recently developed randomized techniques for scalable kernel methods. We show that this structure can be exploited to further accelerate the solution of the regression problem, achieving running times that are faster than "input sparsity". We present empirical results confirming both the practical value of our modeling framework, as well as speedup benefits of randomized regression.
AB - Motivated by the desire to extend fast randomized techniques to nonlinear lp regression, we consider a class of structured regression problems. These problems involve Vandermonde matrices which arise naturally in various statistical modeling settings, including classical polynomial fitting problems, additive models and approximations to recently developed randomized techniques for scalable kernel methods. We show that this structure can be exploited to further accelerate the solution of the regression problem, achieving running times that are faster than "input sparsity". We present empirical results confirming both the practical value of our modeling framework, as well as speedup benefits of randomized regression.
UR - http://www.scopus.com/inward/record.url?scp=84899019943&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???
AN - SCOPUS:84899019943
SN - 1049-5258
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 27th Annual Conference on Neural Information Processing Systems, NIPS 2013
Y2 - 5 December 2013 through 10 December 2013
ER -