gradient-clipping

Tag

Cards List
#gradient-clipping

RAPTOR: Role-Aware Private Training for Mixture-of-Experts

arXiv cs.LG ↗ · 2026-09-10 Cached

RAPTOR is a role-aware framework for differentially private fine-tuning of Mixture-of-Experts models, addressing failure modes like clipping interference and noise dilution, with experimental improvements over standard DP baselines.

0 favorites 0 likes
← Back to home

Submit Feedback