Regret Bounds for Lifelong Learning
[edit]
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:261269, 2017.
Abstract
We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a withintask algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the withintask algorithm, thereby transferring information from one task to the next. We show that when the withintask 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 $O(1/\sqrtm)$ bounds to $O(1/m)$, where $m$ is the per task sample size.
Related Material


