Stateless Neural Meta-Learning using Second-Order Gradients

2021-04-21 · Mike Huisman, Aske Plaat, Jan N. van Rijn

Deep learning typically requires large data sets and much compute power for each new problem that is learned. Meta-learning can be used to learn a good prior that facilitates quick learning, thereby relaxing these requirements so that new tasks can be learned quicker; two popular approaches are MAML and the meta-learner LSTM. In this work, we compare the two and formally show that the meta-learner LSTM subsumes MAML. Combining this insight with recent empirical findings, we construct a new algorithm (dubbed TURTLE) which is simpler than the meta-learner LSTM yet more expressive than MAML. TURTLE outperforms both techniques at few-shot sine wave regression and image classification on miniImageNet and CUB without any additional hyperparameter tuning, at a computational cost that is comparable with second-order MAML. The key to TURTLE's success lies in the use of second-order gradients, which also significantly increases the performance of the meta-learner LSTM by 1-6% accuracy.

📄 PDF Abstract BibTeX arXiv:2104.10527

Code (1)

mikehuisman/revisiting-learned-optimizers 공식 구현 pytorch

Tasks

image-classification Image Classification Meta-Learning

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음

Sigmoid Activation 설명 없음

MAML 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

A Better Baseline for Second Order Gradient Estimation in Stochastic Computation Graphs

2018-09-27 · Jingkai Mao, Jakob Foerster, Tim Rocktäschel, Gregory Farquhar 외

Motivated by the need for higher order gradients in multi-agent reinforcement learning and meta-learning, this paper studies the construction of baselines for second order Monte Carlo gradient estimators in order to redu…

Meta-Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

2021-06-19 · NeurIPS 2021 12 · Ondrej Bohdal, Yongxin Yang, Timothy Hospedales

Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing a…

Cross-Domain Few-Shot cross-domain few-shot learning Few-Shot Learning Hyperparameter Optimization+1

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

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

2019-10-09 · ICLR 2020 1 · Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distill…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics

2026-01-22 · Sukesh Subaharan arxiv

Large language model (LLM) agents often exhibit abrupt shifts in tone and persona during extended interaction, reflecting the absence of explicit temporal structure governing agent-level state. While prior work emphasize…

Emotion Classification