Regret Bounds for Lifelong Learning
Pierre Alquier, The Tien Mai, Massimiliano Pontil
Abstract
We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the within-task algorithm, thereby transferring information from one task to the next. We show that when the within-task algorithm comes with some regret bound, our strategy inherits this good property. Our bounds are in expectation for a general loss function, and uniform for a convex loss. We discuss applications to dictionary learning and finite set of predictors. In the latter case, we improve previous $O(1/\sqrt{m})$ bounds to $O(1/m)$, where $m$ is the per task sample size.
BibTeX
@InProceedings{pmlr-v54-alquier17a,
title = {{Regret Bounds for Lifelong Learning}},
author = {Alquier, Pierre and Mai, The Tien and Pontil, Massimiliano},
booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics},
pages = {261--269},
year = {2017},
editor = {Singh, Aarti and Zhu, Jerry},
volume = {54},
series = {Proceedings of Machine Learning Research},
month = {20--22 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v54/alquier17a/alquier17a.pdf},
url = {https://proceedings.mlr.press/v54/alquier17a.html},
abstract = {We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the within-task algorithm, thereby transferring information from one task to the next. We show that when the within-task algorithm comes with some regret bound, our strategy inherits this good property. Our bounds are in expectation for a general loss function, and uniform for a convex loss. We discuss applications to dictionary learning and finite set of predictors. In the latter case, we improve previous $O(1/\sqrt{m})$ bounds to $O(1/m)$, where $m$ is the per task sample size.}
}