Regret Bounds for Lifelong Learning
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:261-269, 2017.
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 $O(1/\sqrtm)$ bounds to $O(1/m)$, where $m$ is the per task sample size.