Time--Data Tradeoffs by Aggressive Smoothing
Abstract
This paper proposes a tradeoff between sample complexity and computation time that applies to statistical estimators based on convex optimization. As the amount of data increases, we can smooth optimization problems more and more aggressively to achieve accurate estimates more quickly. This work provides theoretical and experimental evidence of this tradeoff for a class of regularized linear inverse problems.
Cite
Text
Bruer et al. "Time--Data Tradeoffs by Aggressive Smoothing." Neural Information Processing Systems, 2014.Markdown
[Bruer et al. "Time--Data Tradeoffs by Aggressive Smoothing." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/bruer2014neurips-time/)BibTeX
@inproceedings{bruer2014neurips-time,
title = {{Time--Data Tradeoffs by Aggressive Smoothing}},
author = {Bruer, John J and Tropp, Joel A and Cevher, Volkan and Becker, Stephen},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {1664-1672},
url = {https://mlanthology.org/neurips/2014/bruer2014neurips-time/}
}