Privacy-Aware Collaborative and Distributed Bayesian Optimization
arXiv:2607.11600
summary
The paper introduces a collaborative meta‑learning framework for distributed Bayesian optimization that avoids sharing raw data, examines privacy leaks from gradient sharing, and evaluates a differentially private defense with its privacy‑utility trade‑off.
Abstract
We propose a collaborative meta-learning framework for distributed Bayesian optimization matching centralized performance without raw-data exchange. We show gradient sharing leaks client observations, with leakage worsening as the search converges and queries concentrate near the optimum. We evaluate a differentially private defense and characterize its privacy-utility trade-off.
6 pages, 5 figures
Topics & keywords
#bayesian optimization#meta-learning#privacy#distributed learning#differential privacycollaborative meta-learninggradient sharingprivacy leakagedifferential privacyprivacy-utility tradeoff