Artificial neural networks thrive in solving the classification problem for a particular rigid task,
acquiring knowledge through generalized learning behaviour from a distinct training phase …

A central capability of intelligent systems is the ability to continuously build upon previous
experiences to speed up and enhance learning of new tasks. Two distinct research …

This paper studies few-shot learning via representation learning, where one uses $ T $
source tasks with $ n_1 $ data per task to learn a representation in order to reduce the …

We build a theoretical framework for designing and understanding practical meta-learning
methods that integrates sophisticated formalizations of task-similarity with the extensive …

We study the convergence of a class of gradient-based Model-Agnostic Meta-Learning
(MAML) methods and characterize their overall complexity as well as their best achievable …

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate
learning of novel future tasks. Under the assumption that future tasks are 'related'to previous …

We study the problem of meta-learning through the lens of online convex optimization,
developing a meta-algorithm bridging the gap between popular gradient-based meta …

Meta-learning aims to perform fast adaptation on a new task through learning a “prior” from
multiple existing tasks. A common practice in meta-learning is to perform a train-validation …

We study the problem of learning-to-learn: infer-ring a learning algorithm that works well on
a family of tasks sampled from an unknown distribution. As class of algorithms we consider …

We address the problem of meta-learning which learns a prior over hypothesis from a
sample of meta-training tasks for fast adaptation on meta-testing tasks. A particularly simple …