Bayesian Model-Agnostic Meta-Learning
Jaesik Yoon · Taesup Kim · Ousmane Dia · Sungwoong Kim · Yoshua Bengio · Sungjin Ahn

Tue Dec 4th 03:40 -- 03:45 PM @ Room 220 E

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 gradient-based 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.

Author Information

Jaesik Yoon (SAP)
Taesup Kim (Université de Montréal)
Ousmane Dia (Element AI)
Sungwoong Kim (Kakao Brain)
Yoshua Bengio (U. Montreal)
Sungjin Ahn (Rutgers University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors