English

Online Meta-Learning

Machine Learning 2019-07-05 v4 Artificial Intelligence Machine Learning

Abstract

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch. In contrast, online (regret based) learning considers a sequential setting in which problems are revealed one after the other, but conventionally train only a single model without any task-specific adaptation. This work introduces an online meta-learning setting, which merges ideas from both the aforementioned paradigms to better capture the spirit and practice of continual lifelong learning. We propose the follow the meta leader algorithm which extends the MAML algorithm to this setting. Theoretically, this work provides an O(logT)\mathcal{O}(\log T) regret guarantee with only one additional higher order smoothness assumption in comparison to the standard online setting. Our experimental evaluation on three different large-scale tasks suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches.

Keywords

Cite

@article{arxiv.1902.08438,
  title  = {Online Meta-Learning},
  author = {Chelsea Finn and Aravind Rajeswaran and Sham Kakade and Sergey Levine},
  journal= {arXiv preprint arXiv:1902.08438},
  year   = {2019}
}

Comments

ICML 2019. The first two authors contributed equally. Expanded Appendix