Private Learning on Networks: Part II
Preprint
Abstract
This paper considers a distributed multi-agent optimization problem, with the global objective consisting of the sum of local objective functions of the agents. The agents solve the optimization problem using local computation and communication between adjacent agents in the network. We present two randomized iterative algorithms for distributed optimization. To improve privacy, our algorithms add "structured" randomization to the information exchanged between the agents. We prove deterministic correctness (in every execution) of the proposed algorithms despite the information being perturbed by noise with non-zero mean. We prove that a special case of a proposed algorithm (called function sharing) preserves privacy of individual polynomial objective functions under a suitable connectivity condition on the network topology.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Fast Distributed Gradient MethodsIEEE Transactions on Automatic Control, 2014
- Distributed delayed stochastic optimization2012
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network ScalingIEEE Transactions on Automatic Control, 2011
- Privacy-preserving horizontally partitioned linear programsOptimization Letters, 2010
- Asynchronous Broadcast-Based Convex Optimization Over a NetworkIEEE Transactions on Automatic Control, 2010
- Distributed Stochastic Subgradient Projection Algorithms for Convex OptimizationJournal of Optimization Theory and Applications, 2010
- Distributed Subgradient Methods for Multi-Agent OptimizationIEEE Transactions on Automatic Control, 2009
- Optimal Scaling of a Gradient Method for Distributed Resource AllocationJournal of Optimization Theory and Applications, 2006
- Information Flow and Cooperative Control of Vehicle FormationsIEEE Transactions on Automatic Control, 2004
- Algebraic Graph Theory2001