Time–Data Tradeoffs by Aggressive Smoothing
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.
© 2014 Neural Information Processing Systems. JJB's and JAT's work was supported under ONR award N00014-11-1002, AFOSR award FA9550-09-1-0643, and a Sloan Research Fellowship. VC's work was supported in part by the European Commission under Grant MIRG-268398, ERC Future Proof, SNF 200021-132548, SNF 200021-146750 and SNF CRSII2-147633. SRB was previously with IBM Research, Yorktown Heights, NY 10598 during the completion of this work.
||524.1 kB||Preview Download|