@inproceedings{flaspohler2021online,
author = {Flaspohler, Genevieve and Orabona, Francesco and Cohen, Judah and Mouatadid, Soukayna and Oprescu, Miruna and Orenstein, Paulo and Mackey, Lester},
title = {Online Learning with Optimism and Delay},
booktitle = {2021 International Conference on Machine Learning},
year = {2021},
month = {July},
abstract = {Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms -- DORM, DORM+, and AdaHedgeD -- arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints can mitigate the regret penalty caused by delay. We pair this delay-as-optimism perspective with a new analysis of optimistic learning that exposes its robustness to hinting errors and a new meta-algorithm for learning effective hinting strategies in the presence of delay. We conclude by benchmarking our algorithms on four subseasonal climate forecasting tasks, demonstrating low regret relative to state-of-the-art forecasting models.},
url = {http://approjects.co.za/?big=en-us/research/publication/online-learning-with-optimism-and-delay/},
}