NeurIPS 2020poster23 citations
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
Yihan Zhou, Victor Sanches Portella, Mark Schmidt, Nicholas Harvey
Abstract
In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret. Moreover, many algorithms have only logarithmic regret when these functions are also strongly convex. Recently, researchers from convex optimization proposed the notions of
BibTeX
@inproceedings{NEURIPS2020_b67fb336,
author = {Zhou, Yihan and Sanches Portella, Victor and Schmidt, Mark and Harvey, Nicholas},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {15823--15833},
publisher = {Curran Associates, Inc.},
title = {Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/b67fb3360ae5597d85a005153451dd4e-Paper.pdf},
volume = {33},
year = {2020}
}