How to train your MAMLDownload PDF

Sep 27, 2018 (edited Feb 25, 2019)ICLR 2019 Conference Blind SubmissionReaders: Everyone
  • Abstract: The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem.Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAML, which we call MAML++.
  • Keywords: meta-learning, deep-learning, few-shot learning, supervised learning, neural-networks, stochastic optimization
  • TL;DR: MAML is great, but it has many problems, we solve many of those problems and as a result we learn most hyper parameters end to end, speed-up training and inference and set a new SOTA in few-shot learning
13 Replies