A privacy-masking learning algorithm for online distributed optimization over time-varying unbalanced digraphs
Summary: This paper investigates a constrained distributed optimization problem enabled by differential privacy where the underlying network is time-changing with unbalanced digraphs. To solve such a problem, we first propose a differentially private online distributed algorithm by injecting adaptively adjustable Laplace noises. The proposed algorithm can not only protect the privacy of participants without compromising a trusted third party, but also be implemented on more general time-varying unbalanced digraphs. Under mild conditions, we then show that the proposed algorithm can achieve a sublinear expected bound of regret for general local convex objective functions. The result shows that there is a trade-off between the optimization accuracy and privacy level. Finally, numerical simulations are conducted to validate the efficiency of the proposed algorithm.
- Privacy-preserving dual stochastic push-sum algorithm for distributed constrained optimization
- Differentially private distributed optimization for multi-agent systems via the augmented Lagrangian algorithm
- An adaptive online learning algorithm for distributed convex optimization with coupled constraints over unbalanced directed graphs
- Gradient-tracking based differentially private distributed optimization with enhanced optimization accuracy
- Distributed online bandit linear regressions with differential privacy
- A Saddle Point Algorithm for Networked Online Convex Optimization
- Cloud-Enabled Differentially Private Multiagent Optimization With Constraints
- Differentially Private Distributed Convex Optimization via Functional Perturbation
- Distributed convex optimization with coupling constraints over time-varying directed graphs
- Distributed Convex Optimization with Inequality Constraints over Time-Varying Unbalanced Digraphs
- Distributed Online Convex Optimization on Time-Varying Directed Graphs
- Distributed Online Optimization in Dynamic Environments Using Mirror Descent
- Distributed optimization over directed graphs with row stochasticity and constraint regularity
- Distributed Optimization Over Time-Varying Directed Graphs
- Distributed Projection Subgradient Algorithm Over Time-Varying General Unbalanced Directed Graphs
- Distributed Subgradient Projection Algorithm Over Directed Graphs
- Online learning and online convex optimization
- Privacy preserving distributed optimization using homomorphic encryption
- Privacy-Preserving Distributed Online Optimization Over Unbalanced Digraphs via Subgradient Rescaling
- Push–Pull Gradient Methods for Distributed Optimization in Networks
- Differentially private distributed algorithms for stochastic aggregative games
- Privacy-preserving dual stochastic push-sum algorithm for distributed constrained optimization
- Differentially private distributed logistic regression with the objective function perturbation
- Differentially private resilient distributed cooperative online estimation over digraphs
- Distributed online bandit linear regressions with differential privacy
- Differentially private distributed online learning over time‐varying digraphs via dual averaging
- Decentralized nonconvex optimization with guaranteed privacy and accuracy
- A differentially private distributed optimization method for constrained optimization
- Gradient-tracking based differentially private distributed optimization with enhanced optimization accuracy
- Privacy preserving distributed online projected residual feedback optimization over unbalanced directed graphs
- A finite time discrete distributed learning algorithm using stochastic configuration network
- Privacy-preserving distributed projected one-point bandit online optimization over directed graphs
This page was built for publication: A privacy-masking learning algorithm for online distributed optimization over time-varying unbalanced digraphs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2051672)
