Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new …
Y Lee, S Choi - International Conference on Machine …, 2018 - proceedings.mlr.press
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 …
C Finn, P Abbeel, S Levine - International conference on …, 2017 - proceedings.mlr.press
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 …
H Peng - arXiv preprint arXiv:2004.11149, 2020 - arxiv.org
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 …