The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Meta-learning researchers face two fundamental issues in their empirical work: prototyping
and reproducibility. Researchers are prone to make mistakes when prototyping new …

Gradient-based meta-learning methods leverage gradient descent to learn the
commonalities among various tasks. While previous such methods have been successful in …

Deep learning has achieved remarkable success in many machine learning tasks such as
image classification, speech recognition, and game playing. However, these breakthroughs …

Meta-learning, or learning to learn, is the science of systematically observing how different
machine learning approaches perform on a wide range of learning tasks, and then learning …

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is
compatible with any model trained with gradient descent and applicable to a variety of …

Although model-agnostic meta-learning (MAML) is a very successful algorithm in meta-
learning practice, it can have high computational cost because it updates all model …

We derive a novel information-theoretic analysis of the generalization property of meta-
learning algorithms. Concretely, our analysis proposes a generic understanding in both the …

The constant introduction of standardized benchmarks in the literature has helped
accelerating the recent advances in meta-learning research. They offer a way to get a fair …

This article reviews meta-learning also known as learning-to-learn which seeks rapid and
accurate model adaptation to unseen tasks with applications in highly automated AI, few …