Online Learning to Rank with Features
Abstract
We introduce a new model for online ranking in which the click probability factors into an examination and attractiveness function and the attractiveness function is a linear function of a feature vector and an unknown parameter. Only relatively mild assumptions are made on the examination function. A novel algorithm for this setup is analysed, showing that the dependence on the number of items is replaced by a dependence on the dimension, allowing the new algorithm to handle a large number of items. When reduced to the orthogonal case, the regret of the algorithm improves on the state-of-the-art.
Cite
Text
Li et al. "Online Learning to Rank with Features." International Conference on Machine Learning, 2019.Markdown
[Li et al. "Online Learning to Rank with Features." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/li2019icml-online/)BibTeX
@inproceedings{li2019icml-online,
title = {{Online Learning to Rank with Features}},
author = {Li, Shuai and Lattimore, Tor and Szepesvari, Csaba},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {3856-3865},
volume = {97},
url = {https://mlanthology.org/icml/2019/li2019icml-online/}
}