From External to Internal Regret
Abstract
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares the loss of an online algorithm to the loss of a modified online algorithm, which consistently replaces one action by another.
Cite
Text
Blum and Mansour. "From External to Internal Regret." Journal of Machine Learning Research, 2007.Markdown
[Blum and Mansour. "From External to Internal Regret." Journal of Machine Learning Research, 2007.](https://mlanthology.org/jmlr/2007/blum2007jmlr-external/)BibTeX
@article{blum2007jmlr-external,
title = {{From External to Internal Regret}},
author = {Blum, Avrim and Mansour, Yishay},
journal = {Journal of Machine Learning Research},
year = {2007},
pages = {1307-1324},
volume = {8},
url = {https://mlanthology.org/jmlr/2007/blum2007jmlr-external/}
}