Bayesian Model-Agnostic Meta-Learning

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

Introduction:

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, the authors propose a novel Bayesian model-agnostic meta-learning method.

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 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.

You may want to know: