Large-scale Riemannian meta-optimization via subspace adaptation

Open Webpage

Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan, Yunde Jia

Published: 01 Jan 2025, Last Modified: 16 May 2025Comput. Vis. Image Underst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•An efficient Riemannian meta-optimization method for large-scale optimization.•A subspace adaptation scheme for parameter sharing in Riemannian meta-optimization.•Reduce memory consumption of optimizing neural networks by six orders of magnitude.