paper-with-me

홈 › Papers

On the Subspace Structure of Gradient-Based Meta-Learning

2022-07-08 · Gustaf Tegnér, Alfredo Reichlin, Hang Yin, Mårten Björkman, Danica Kragic

In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods. Previous work has noticed how, for the case of image-classification, this adaptation only takes place on the last layers of the network. We propose the more general notion that parameters are updated over a low-dimensional \emph{subspace} of the same dimensionality as the task-space and show that this holds for regression as well. Furthermore, the induced subspace structure provides a method to estimate the intrinsic dimension of the space of tasks of common few-shot learning datasets.

📄 PDF Abstract BibTeX arXiv:2207.03804

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learningimage-classificationImage ClassificationMeta-Learningregression

Similar Papers 제목 키워드 기반

Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

2018-01-17 · ICML 2018 7 · Yoonho Lee, Seungjin Choi

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient desce…

Few-Shot Image ClassificationMeta-Learning

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation

2025-01-25 · Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan 외

Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimization on Riemannian manifolds. However, exi…

Multi-Subspace Structured Meta-Learning

2021-09-29 · Weisen Jiang, James Kwok, Yu Zhang

Meta-learning aims to extract meta-knowledge from historical tasks to accelerate learning on new tasks. A critical challenge in meta-learning is to handle task heterogeneity, i.e., tasks lie in different distributions. U…

Meta-Learning

Subspace Adaptation Prior for Few-Shot Learning

2023-10-13 · Mike Huisman, Aske Plaat, Jan N. van Rijn

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved succ…

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification+1

Online Supervised Subspace Tracking

2015-09-01 · Yao Xie, Ruiyang Song, Hanjun Dai, Qingbin Li 외

We present a framework for supervised subspace tracking, when there are two time series $x_t$ and $y_t$, one being the high-dimensional predictors and the other being the response variables and the subspace tracking need…

Dimensionality ReductionregressionTime SeriesTime Series Analysis