Quantization Enabled Privacy Protection in Decentralized Stochastic Optimization
From MaRDI portal
Abstract: By enabling multiple agents to cooperatively solve a global optimization problem in the absence of a central coordinator, decentralized stochastic optimization is gaining increasing attention in areas as diverse as machine learning, control, and sensor networks. Since the associated data usually contain sensitive information, such as user locations and personal identities, privacy protection has emerged as a crucial need in the implementation of decentralized stochastic optimization. In this paper, we propose a decentralized stochastic optimization algorithm that is able to guarantee provable convergence accuracy even in the presence of aggressive quantization errors that are proportional to the amplitude of quantization inputs. The result applies to both convex and non-convex objective functions, and enables us to exploit aggressive quantization schemes to obfuscate shared information, and hence enables privacy protection without losing provable optimization accuracy. In fact, by using a {stochastic} ternary quantization scheme, which quantizes any value to three numerical levels, we achieve quantization-based rigorous differential privacy in decentralized stochastic optimization, which has not been reported before. In combination with the presented quantization scheme, the proposed algorithm ensures, for the first time, rigorous differential privacy in decentralized stochastic optimization without losing provable convergence accuracy. Simulation results for a distributed estimation problem as well as numerical experiments for decentralized learning on a benchmark machine learning dataset confirm the effectiveness of the proposed approach.
Recommendations
- Decentralized Stochastic Optimization With Inherent Privacy Protection
- Enabling Privacy-Preservation in Decentralized Optimization
- Decentralized nonconvex optimization with guaranteed privacy and accuracy
- Dynamics based privacy preservation in decentralized optimization
- Optimal Local Differentially Private Quantization
- Quadratic Error Minimization in a Distributed Environment with Privacy Preserving
- Privacy preserving distributed optimization using homomorphic encryption
- Privacy-preserving federated learning on lattice quantization
- Privacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework
Cited in
(10)- Quadratic Error Minimization in a Distributed Environment with Privacy Preserving
- Enabling Privacy-Preservation in Decentralized Optimization
- Privacy-preserving federated learning on lattice quantization
- Decentralized Stochastic Optimization With Inherent Privacy Protection
- Dynamics based privacy preservation in decentralized optimization
- Differentially private dual gradient tracking for distributed resource allocation
- Broadcast-based asynchronous convex optimization using quantized distributed stochastic mirror descent algorithm
- Differentially private and communication-efficient distributed nonconvex optimization algorithms
- Privacy-preserving resilient bipartite consensus of multi-agent systems: a differential privacy scheme
- Privacy-preserving gradient tracking via state decomposition for directed multi-agent optimization
This page was built for publication: Quantization Enabled Privacy Protection in Decentralized Stochastic Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6080210)
