paper-with-me

홈 › Papers

Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD

2021-09-15 · Chen Fan, Parikshit Ram, Sijia Liu

We propose a new computationally-efficient first-order algorithm for Model-Agnostic Meta-Learning (MAML). The key enabling technique is to interpret MAML as a bilevel optimization (BLO) problem and leverage the sign-based SGD(signSGD) as a lower-level optimizer of BLO. We show that MAML, through the lens of signSGD-oriented BLO, naturally yields an alternating optimization scheme that just requires first-order gradients of a learned meta-model. We term the resulting MAML algorithm Sign-MAML. Compared to the conventional first-order MAML (FO-MAML) algorithm, Sign-MAML is theoretically-grounded as it does not impose any assumption on the absence of second-order derivatives during meta training. In practice, we show that Sign-MAML outperforms FO-MAML in various few-shot image classification tasks, and compared to MAML, it achieves a much more graceful tradeoff between classification accuracy and computation efficiency.

📄 PDF Abstract BibTeX arXiv:2109.07497

Code (1)

chenfan95/sign-maml 공식 구현 pytorch

Tasks

Bilevel OptimizationFew-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Similar Papers 제목 키워드 기반

Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?

2022-03-06 · Lisha Chen, Tianyi Chen

Meta learning aims at learning a model that can quickly adapt to unseen tasks. Widely used meta learning methods include model agnostic meta learning (MAML), implicit MAML, Bayesian MAML. Thanks to its ability of modelin…

Meta-Learningmodel

Directed-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation

2025-09-30 · Yang Zhang, Huiwen Yan, Mushuang Liu arxiv

Model-Agnostic Meta-Learning (MAML) is a versatile meta-learning framework applicable to both supervised learning and reinforcement learning (RL). However, applying MAML to meta-reinforcement learning (meta-RL) presents …

Computational EfficiencyReinforcement Learning

When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications

2020-05-24 · Zequn Liu, Ruiyi Zhang, Yiping Song, Wei Ju 외

Model-Agnostic Meta-Learning (MAML), a model-agnostic meta-learning method, is successfully employed in NLP applications including few-shot text classification and multi-domain low-resource language generation. Many impa…

Few-Shot Text ClassificationLanguage ModelingLanguage ModellingMeta-Learning+3

Alpha MAML: Adaptive Model-Agnostic Meta-Learning

2019-05-17 · Harkirat Singh Behl, Atılım Güneş Baydin, Philip H. S. Torr

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on fe…

Few-Shot LearningGeneral ClassificationMeta-Learningmodel+1

Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning

2022-06-08 · Momin Abbas, Quan Xiao, Lisha Chen, Pin-Yu Chen 외

Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem struct…

Meta-Learningmodel