Cosimo Aprile, Alessandro Cevrero, et al.
IEEE JSSC
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.
Cosimo Aprile, Alessandro Cevrero, et al.
IEEE JSSC
Aleksandr Aravkin, Stephen Becker, et al.
UAI 2014
Alessandro Cevrero, Cosimo Aprile, et al.
VLSI Circuits 2015
Bubacarr Bah, Stephen Becker, et al.
ICASSP 2014