Private Learning on Networks: Part II
Authors:
Preprint
Abstract
Widespread deployment of distributed machine learning algorithms has raised new privacy challenges. The focus of this paper is on improving privacy of each participant's local information (such as dataset or loss function) while collaboratively learning underlying model. We present two iterative algorithms for privacy preserving distributed learning. Our algorithms involves adding structured randomization to the state estimates. We prove deterministic correctness (in every execution) of our algorithm despite the iterates being perturbed by non-zero mean random variables. We motivate privacy using privacy analysis of a special case of our algorithm referred to as Function Sharing strategy (presented in [1]).Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Differentially Private Distributed Convex Optimization via Functional PerturbationIEEE Transactions on Control of Network Systems, 2016
- Differentially Private Distributed Constrained OptimizationIEEE Transactions on Automatic Control, 2016
- Robust Distributed Average Consensus via Exchange of Running SumsIEEE Transactions on Automatic Control, 2015
- Distributed Optimization Over Time-Varying Directed GraphsIEEE Transactions on Automatic Control, 2014
- 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
- Distributed average consensus with least-mean-square deviationJournal of Parallel and Distributed Computing, 2007
- Information Flow and Cooperative Control of Vehicle FormationsIEEE Transactions on Automatic Control, 2004