Litcius/Paper detail

Robust Constrained Consensus and Inequality-Constrained Distributed Optimization With Guaranteed Differential Privacy and Accurate Convergence

Yongqiang Wang, Angelia Nedić

2024IEEE Transactions on Automatic Control19 citationsDOI

Abstract

We address differential privacy for fully distributed optimization subject to a shared inequality constraint. By co-designing the distributed optimization mechanism and the differential-privacy noise injection mechanism, we propose the first distributed constrained optimization algorithm that can ensure both provable convergence to a global optimal solution and rigorous <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> -differential privacy, even when the number of iterations tends to infinity. Our approach does not require the Lagrangian function to be strictly convex/concave, and allows the global objective function to be non-separable. As a byproduct of the co-design, we also propose a new constrained consensus algorithm that can achieve rigorous <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> -differential privacy while maintaining accurate convergence, which, to our knowledge, has not been achieved before. Numerical simulation results on a demand response control problem in smart grid confirm the effectiveness of the proposed approach.

Topics & Concepts

Convergence (economics)Differential privacyComputer scienceMathematical optimizationConsensusInequalityMathematicsControl theory (sociology)Multi-agent systemControl (management)EconomicsAlgorithmArtificial intelligenceEconomic growthMathematical analysisDistributed Control Multi-Agent SystemsOptimization and Search ProblemsStochastic Gradient Optimization Techniques
Robust Constrained Consensus and Inequality-Constrained Distributed Optimization With Guaranteed Differential Privacy and Accurate Convergence | Litcius