Abstract | ||
---|---|---|
Due to the inherent model uncertainty, learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines efficient gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. Unlike previous methods, during fast adaptation, the method is capable of learning complex uncertainty structure beyond a simple Gaussian approximation, and during meta-update, a novel Bayesian mechanism prevents meta-level overfitting. Remaining a gradientbased method, it is also the first Bayesian model-agnostic meta-learning method applicable to various tasks including reinforcement learning. Experiment results show the accuracy and robustness of the proposed method in sinusoidal regression, image classification, active learning, and reinforcement learning. |
Year | Venue | DocType |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | Conference |
Volume | ISSN | Citations |
31 | 1049-5258 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jaesik Yoon | 1 | 0 | 0.68 |
Taesup Kim | 2 | 57 | 3.23 |
Ousmane Amadou Dia | 3 | 0 | 1.69 |
Sungwoong Kim | 4 | 76 | 5.10 |
Yoshua Bengio | 5 | 42677 | 3039.83 |
Ahn, Sungjin | 6 | 0 | 3.72 |