Computational and Statistical Tradeoffs in Learning to Rank
Abstract
For massive and heterogeneous modern data sets, it is of fundamental interest to provide guarantees on the accuracy of estimation when computational resources are limited. In the application of learning to rank, we provide a hierarchy of rank-breaking mechanisms ordered by the complexity in thus generated sketch of the data. This allows the number of data points collected to be gracefully traded off against computational resources available, while guaranteeing the desired level of accuracy. Theoretical guarantees on the proposed generalized rank-breaking implicitly provide such trade-offs, which can be explicitly characterized under certain canonical scenarios on the structure of the data.
Cite
Text
Khetan and Oh. "Computational and Statistical Tradeoffs in Learning to Rank." Neural Information Processing Systems, 2016.Markdown
[Khetan and Oh. "Computational and Statistical Tradeoffs in Learning to Rank." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/khetan2016neurips-computational/)BibTeX
@inproceedings{khetan2016neurips-computational,
title = {{Computational and Statistical Tradeoffs in Learning to Rank}},
author = {Khetan, Ashish and Oh, Sewoong},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {739-747},
url = {https://mlanthology.org/neurips/2016/khetan2016neurips-computational/}
}