# On the Subspace Structure of Gradient-Based Meta-Learning

Source: [On the Subspace Structure of Gradient-Based Meta-Learning](<https://www.sota2.com/research/paper/68fa6d831e209131cea3a41e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:36:22.217Z

Authors: Gustaf Tegn\\'er, Alfredo Reichlin, Hang Yin, M{\\aa}rten Bj\\"orkman, Danica Kragic

Published: 2022-07-08T10:19:15.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.03804>)

[PDF](<https://arxiv.org/pdf/2207.03804.pdf>)