Meta-Learning with Adaptive Hyperparameters
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Baik, Sungyong | - |
dc.contributor.author | Choi, Myungsub | - |
dc.contributor.author | Choi, Janghoon | - |
dc.contributor.author | Kim, Heewon | - |
dc.contributor.author | Lee, Kyoung Mu | - |
dc.date.accessioned | 2023-10-04T06:57:05Z | - |
dc.date.available | 2023-10-04T06:57:05Z | - |
dc.date.created | 2023-07-19 | - |
dc.date.issued | 2020-12 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/191686 | - |
dc.description.abstract | Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization. Instead of searching for better task-aware initialization, we focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation). Consequently, we propose a new weight update rule that greatly enhances the fast adaptation process. Specifically, we introduce a small meta-network that can adaptively generate per-step hyperparameters: learning rate and weight decay coefficients. The experimental results validate that the Adaptive Learning of hyperparameters for Fast Adaptation (ALFA) is the equally important ingredient that was often neglected in the recent few-shot learning approaches. Surprisingly, fast adaptation from random initialization with ALFA can already outperform MAML. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Curran Associates | - |
dc.title | Meta-Learning with Adaptive Hyperparameters | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Baik, Sungyong | - |
dc.identifier.bibliographicCitation | Conference on Neural Information Processing Systems, pp.20755 - 20765 | - |
dc.relation.isPartOf | Conference on Neural Information Processing Systems | - |
dc.citation.title | Conference on Neural Information Processing Systems | - |
dc.citation.startPage | 20755 | - |
dc.citation.endPage | 20765 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 3 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.identifier.url | https://arxiv.org/abs/2011.00209 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.