Mallows Models for Top-K Lists

Abstract

The classic Mallows model is a widely-used tool to realize distributions on per- mutations. Motivated by common practical situations, in this paper, we generalize Mallows to model distributions on top-k lists by using a suitable distance measure between top-k lists. Unlike many earlier works, our model is both analytically tractable and computationally efficient. We demonstrate this by studying two basic problems in this model, namely, sampling and reconstruction, from both algorithmic and experimental points of view.

Cite

Text

Chierichetti et al. "Mallows Models for Top-K Lists." Neural Information Processing Systems, 2018.

Markdown

[Chierichetti et al. "Mallows Models for Top-K Lists." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/chierichetti2018neurips-mallows/)

BibTeX

@inproceedings{chierichetti2018neurips-mallows,
  title     = {{Mallows Models for Top-K Lists}},
  author    = {Chierichetti, Flavio and Dasgupta, Anirban and Haddadan, Shahrzad and Kumar, Ravi and Lattanzi, Silvio},
  booktitle = {Neural Information Processing Systems},
  year      = {2018},
  pages     = {4382-4392},
  url       = {https://mlanthology.org/neurips/2018/chierichetti2018neurips-mallows/}
}