Normalized Online Learning
Abstract
We introduce online learning algorithms which are independent of feature scales, proving regret bounds dependent on the ratio of scales existent in the data rather than the absolute scale. This has several useful effects: there is no need to pre-normalize data, the test-time and test-space complexity are reduced, and the algorithms are more robust.
Cite
Text
Ross et al. "Normalized Online Learning." Conference on Uncertainty in Artificial Intelligence, 2013.Markdown
[Ross et al. "Normalized Online Learning." Conference on Uncertainty in Artificial Intelligence, 2013.](https://mlanthology.org/uai/2013/ross2013uai-normalized/)BibTeX
@inproceedings{ross2013uai-normalized,
title = {{Normalized Online Learning}},
author = {Ross, Stéphane and Mineiro, Paul and Langford, John},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2013},
url = {https://mlanthology.org/uai/2013/ross2013uai-normalized/}
}