Abstract | ||
---|---|---|
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. During fast adaptation, the method is capable of learning complex uncertainty structure beyond a point estimate or a simple Gaussian approximation. In addition, a robust Bayesian meta-update mechanism with a new meta-loss prevents overfitting during meta-update. Remaining an efficient gradient-based meta-learner, the method is also model-agnostic and simple to implement. Experiment results show the accuracy and robustness of the proposed method in various tasks: sinusoidal regression, image classification, active learning, and reinforcement learning. |
Year | Venue | DocType |
---|---|---|
2018 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1806.03836 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taesup Kim | 1 | 57 | 3.23 |
Jaesik Yoon | 2 | 0 | 0.68 |
Ousmane Amadou Dia | 3 | 0 | 1.69 |
Sungwoong Kim | 4 | 53 | 2.06 |
Yoshua Bengio | 5 | 0 | 17.58 |
Sungjin Ahn | 6 | 7 | 2.83 |