Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?

by   Lisha Chen, et al.

Meta learning aims at learning a model that can quickly adapt to unseen tasks. Widely used meta learning methods include model agnostic meta learning (MAML), implicit MAML, Bayesian MAML. Thanks to its ability of modeling uncertainty, Bayesian MAML often has advantageous empirical performance. However, the theoretical understanding of Bayesian MAML is still limited, especially on questions such as if and when Bayesian MAML has provably better performance than MAML. In this paper, we aim to provide theoretical justifications for Bayesian MAML's advantageous performance by comparing the meta test risks of MAML and Bayesian MAML. In the meta linear regression, under both the distribution agnostic and linear centroid cases, we have established that Bayesian MAML indeed has provably lower meta test risks than MAML. We verify our theoretical results through experiments.


Bayesian Model-Agnostic Meta-Learning

Learning to infer Bayesian posterior from a few-shot dataset is an impor...

Provable Generalization of Overparameterized Meta-learning Trained with SGD

Despite the superior empirical success of deep meta-learning, theoretica...

Distribution-Agnostic Model-Agnostic Meta-Learning

The Model-Agnostic Meta-Learning (MAML) algorithm <cit.> has been celebr...

System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy

Dynamic scheduling is an important problem in applications from queuing ...

ALPaCA vs. GP-based Prior Learning: A Comparison between two Bayesian Meta-Learning Algorithms

Meta-learning or few-shot learning, has been successfully applied in a w...

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

Current state-of-the-art few-shot learners focus on developing effective...

Meta Learning MPC using Finite-Dimensional Gaussian Process Approximations

Data availability has dramatically increased in recent years, driving mo...