
YF
Yizhao Fan, Wenjian Luo, Jiaojiao Zhang
· 1 min read
ResearcharXiv cs.LG
Private Decentralized Optimization with Noise Reduction and Bias Correction
arXiv:2609.27658v1 Announce Type: new
Abstract: Private decentralized learning is affected by sampling noise, privacy noise, and decentralized bias under heterogeneous data. We propose Private Recursive Decentralized Optimization (PRDO). PRDO uses recursive estimation with same-batch gradient differences to reduce estimation errors caused by sampling and privacy noise, while its Exact Diffusion component corrects decentralized bias arising from data heterogeneity. Our analysis establishes a nonconvex convergence bound without assuming uniformly bounded data heterogeneity across nodes. It further gives a sufficient condition under which recursive gradient differences yield strictly lower query sensitivity than private Exact Diffusion, together with an example that rigorously satisfies this condition. Experiments show improved accuracy over the evaluated baselines.
Original source
This story was published by arXiv cs.LG and written by Yizhao Fan, Wenjian Luo, Jiaojiao Zhang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


