On First-Order Meta-Learning Algorithms

2018-03-08 · Alex Nichol, Joshua Achiam, John Schulman

This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.e., learns quickly) when presented with a previously unseen task sampled from this distribution. We analyze a family of algorithms for learning a parameter initialization that can be fine-tuned quickly on a new task, using only first-order derivatives for the meta-learning updates. This family includes and generalizes first-order MAML, an approximation to MAML obtained by ignoring second-order derivatives. It also includes Reptile, a new algorithm that we introduce here, which works by repeatedly sampling a task, training on it, and moving the initialization towards the trained weights on that task. We expand on the results from Finn et al. showing that first-order meta-learning algorithms perform well on some well-established benchmarks for few-shot classification, and we provide theoretical analysis aimed at understanding why these algorithms work.

📄 PDF Abstract BibTeX arXiv:1803.02999

Code (13)

openai/supervised-reptile 공식 구현 tf

MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/On_First_Order_Meta_Learning_Algorithms pytorch

Yuzhe-CHEN/NerfSNN pytorch

aravindMahadevan/metaLearningAlgos pytorch

gabrielhuang/reptile-pytorch pytorch

gebob19/REPTILE-Metalearning pytorch

gebob19/cscd94-metalearning pytorch

gebob19/cscd94_metalearning pytorch

hfahrudin/reptile_implement_tf2 tf

learnables/learn2learn pytorch

peisungtsai/Reptile-Pytorch-Implementation pytorch

radrumond/Chameleon tf

sanowar-raihan/nerf-meta pytorch

Tasks

Few-Shot Image Classification Few-Shot Learning Meta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Enhancing Generalization of First-Order Meta-Learning

2019-03-22 · ICLR Workshop LLD 2019 · Mirantha Jayathilaka

In this study we focus on first-order meta-learning algorithms that aim to learn a parameter initialization of a network which can quickly adapt to new concepts, given a few examples. We investigate two approaches to enh…

Few-Shot Image Classification image-classification Image Classification Meta-Learning

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 Efficiency Reinforcement Learning

Variance-reduced First-order Meta-learning for Natural Language Processing Tasks

2021-06-01 · NAACL 2021 4 · Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu 외

First-order meta-learning algorithms have been widely used in practice to learn initial model parameters that can be quickly adapted to new tasks due to their efficiency and effectiveness. However, existing studies find …

dialog state tracking Few-Shot Text Classification Meta-Learning text-classification+1

Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent

2021-04-12 · Guangzeng Xie, Hao Jin, Dachao Lin, Zhihua Zhang

We propose \textit{Meta-Regularization}, a novel approach for the adaptive choice of the learning rate in first-order gradient descent methods. Our approach modifies the objective function by adding a regularization term…

Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes

2023-01-17 · Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik

In this work, we consider the problem of minimizing the sum of Moreau envelopes of given functions, which has previously appeared in the context of meta-learning and personalized federated learning. In contrast to the ex…

Federated Learning Meta-Learning Personalized Federated Learning