Meta-learning has gained wide popularity as a training framework that is more data-efficient
than traditional machine learning methods. However, its generalization ability in complex …

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 …

Improving the generalization of deep networks is an important open challenge, particularly
in domains without plentiful data. The mixup algorithm improves generalization by linearly …

The ability to learn new concepts with small amounts of data is a critical aspect of
intelligence that has proven challenging for deep learning methods. Meta-learning has …

Meta-learning algorithms aim to learn two components: a model that predicts targets for a
task, and a base learner that updates that model when given examples from a new task. This …

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few
labeled examples by transferring previously learned knowledge. However, the bottleneck of …

In this paper, we study the generalization properties of Model-Agnostic Meta-Learning
(MAML) algorithms for supervised learning problems. We focus on the setting in which we …

Abstract Model-Agnostic Meta-Learning (MAML) and its variants have achieved success in
meta-learning tasks on many datasets and settings. Nonetheless, we have just started to …

Several papers argue that wide minima generalize better than narrow minima. In this paper,
through detailed experiments that not only corroborate the generalization properties of wide …

Meta-learning methods typically follow a two-loop framework, where each loop potentially
suffers from notorious overfitting, hindering rapid adaptation and generalization to new …