Private Learning on Networks: Part II

• DOI: 10.48550/arxiv.1703.09185
• Publication Date: 2017-01-01
• Authors: Shripad Gade; Nitin H. Vaidya
• Keywords: Distributed learning

This paper considers a distributed multi-agent optimization problem, with the global objective consisting of sum local functions agents. The agents solve problem using computation and communication between adjacent in network. We present two randomized iterative algorithms for optimization. To improve privacy, our add "structured" randomization to information exchanged prove deterministic correctness (in every execution) proposed despite being perturbed by noise non-zero mean. that special case algorithm (called function sharing) preserves privacy individual polynomial under suitable connectivity condition on network topology.