Saved in:
Bibliographic Details
Main Authors: Anjum, Usman, Stockman, Chris, Luong, Cat, Zhan, Justin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.09418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916895737774080
author Anjum, Usman
Stockman, Chris
Luong, Cat
Zhan, Justin
author_facet Anjum, Usman
Stockman, Chris
Luong, Cat
Zhan, Justin
contents This paper introduces Domain Generalization Sharpness-Aware Minimization Model-Agnostic Meta-Learning (DGS-MAML), a novel meta-learning algorithm designed to generalize across tasks with limited training data. DGS-MAML combines gradient matching with sharpness-aware minimization in a bi-level optimization framework to enhance model adaptability and robustness. We support our method with theoretical analysis using PAC-Bayes and convergence guarantees. Experimental results on benchmark datasets show that DGS-MAML outperforms existing approaches in terms of accuracy and generalization. The proposed method is particularly useful for scenarios requiring few-shot learning and quick adaptation, and the source code is publicly available at GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09418
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain-Generalization to Improve Learning in Meta-Learning Algorithms
Anjum, Usman
Stockman, Chris
Luong, Cat
Zhan, Justin
Machine Learning
Artificial Intelligence
This paper introduces Domain Generalization Sharpness-Aware Minimization Model-Agnostic Meta-Learning (DGS-MAML), a novel meta-learning algorithm designed to generalize across tasks with limited training data. DGS-MAML combines gradient matching with sharpness-aware minimization in a bi-level optimization framework to enhance model adaptability and robustness. We support our method with theoretical analysis using PAC-Bayes and convergence guarantees. Experimental results on benchmark datasets show that DGS-MAML outperforms existing approaches in terms of accuracy and generalization. The proposed method is particularly useful for scenarios requiring few-shot learning and quick adaptation, and the source code is publicly available at GitHub.
title Domain-Generalization to Improve Learning in Meta-Learning Algorithms
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.09418