Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost

This paper proposes a tradeoff between computational time, sample complexity, and statistical accuracy that applies to statistical estimators based on convex optimization. When we have a large amount of data, we can exploit excess samples to decrease statistical risk, to decrease computational cost, or to trade off between the two. We propose to achieve this tradeoff by varying the amount of smoothing applied to the optimization problem. This work uses regularized linear regression as a case study to argue for the existence of this tradeoff both theoretically and experimentally. We also apply our method to describe a tradeoff in an image interpolation problem.


Published in:
IEEE Journal of Selected Topics in Signal Processing, 9, 4, 612-624
Year:
2015
Publisher:
Piscataway, Ieee-Inst Electrical Electronics Engineers Inc
ISSN:
1932-4553
Keywords:
Laboratories:




 Record created 2015-02-05, last modified 2018-09-13

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)