FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Client

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Gongxi, Gu, Hanlin, Fan, Lixin, Yang, Qiang, Han, Yuxing
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.12014