TY - GEN
T1 - Online Constrained Meta-Learning
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
AU - Xu, Siyuan
AU - Zhu, Minghui
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - Meta-learning has attracted attention due to its strong ability to learn experiences from known tasks, which can speed up and enhance the learning process for new tasks. However, most existing meta-learning approaches only can learn from tasks without any constraint. This paper proposes an online constrained meta-learning framework, which continuously learns meta-knowledge from sequential learning tasks, and the learning tasks are subject to hard constraints. Beyond existing meta-learning analyses, we provide the upper bounds of optimality gaps and constraint violations of the deployed task-specific models produced by the proposed framework. These metrics consider both the dynamic regret of online learning and the generalization ability of the task-specific models to unseen data. Moreover, we provide a practical algorithm for the framework and validate its superior effectiveness through experiments conducted on meta-imitation learning and few-shot image classification.
AB - Meta-learning has attracted attention due to its strong ability to learn experiences from known tasks, which can speed up and enhance the learning process for new tasks. However, most existing meta-learning approaches only can learn from tasks without any constraint. This paper proposes an online constrained meta-learning framework, which continuously learns meta-knowledge from sequential learning tasks, and the learning tasks are subject to hard constraints. Beyond existing meta-learning analyses, we provide the upper bounds of optimality gaps and constraint violations of the deployed task-specific models produced by the proposed framework. These metrics consider both the dynamic regret of online learning and the generalization ability of the task-specific models to unseen data. Moreover, we provide a practical algorithm for the framework and validate its superior effectiveness through experiments conducted on meta-imitation learning and few-shot image classification.
UR - https://www.scopus.com/pages/publications/85191183955
UR - https://www.scopus.com/pages/publications/85191183955#tab=citedBy
M3 - Conference contribution
AN - SCOPUS:85191183955
T3 - Advances in Neural Information Processing Systems
BT - Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
A2 - Oh, A.
A2 - Neumann, T.
A2 - Globerson, A.
A2 - Saenko, K.
A2 - Hardt, M.
A2 - Levine, S.
PB - Neural information processing systems foundation
Y2 - 10 December 2023 through 16 December 2023
ER -