GradMetaNet: An Equivariant Architecture for Learning on Gradients

Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo Putterman, Haggai Maron

Published: 05 Mar 2025, Last Modified: 05 Mar 2025ICLR 2025 Workshop Weight Space Learning PosterEveryoneRevisionsBibTeXCC BY 4.0
Track: long paper (up to 8 pages)
Keywords: Equivariance, parameter symmetries, gradients, learned optimizers, model editing, curvature
Submission Number: 32