Ensure Differential Privacy and Convergence Accuracy in Consensus Tracking and Aggregative Games with Coupling Constraints
- URL: http://arxiv.org/abs/2210.16395v4
- Date: Tue, 16 Jul 2024 17:03:04 GMT
- Title: Ensure Differential Privacy and Convergence Accuracy in Consensus Tracking and Aggregative Games with Coupling Constraints
- Authors: Yongqiang Wang,
- Abstract summary: We address differential privacy for fully distributed aggregative games with shared coupling constraints.
By co-designing the generalized Nash equilibrium (GNE) seeking mechanism and the differential-privacy noise injection mechanism, we propose the first GNE seeking algorithm.
We also propose a new consensus-tracking algorithm that can achieve rigorous epsilon-differential privacy while maintaining accurate tracking performance.
- Score: 1.8661143694112918
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We address differential privacy for fully distributed aggregative games with shared coupling constraints. By co-designing the generalized Nash equilibrium (GNE) seeking mechanism and the differential-privacy noise injection mechanism, we propose the first GNE seeking algorithm that can ensure both provable convergence to the GNE and rigorous epsilon-differential privacy, even with the number of iterations tending to infinity. As a basis of the co-design, we also propose a new consensus-tracking algorithm that can achieve rigorous epsilon-differential privacy while maintaining accurate tracking performance, which, to our knowledge, has not been achieved before. To facilitate the convergence analysis, we also establish a general convergence result for stochastically-perturbed nonstationary fixed-point iteration processes, which lie at the core of numerous optimization and variational problems. Numerical simulation results confirm the effectiveness of the proposed approach.
Related papers
- Faster Rates For Federated Variational Inequalities [14.218257983404134]
We show that for general smooth and monotone variational inequalities, the classical Local Extra SGD algorithm admits tighter guarantees.<n>We propose a new algorithm, the Local Inexact Proximal Point Algorithm with Extra Step (LIPPAX), which mitigates client drift.<n>We extend our results to federated composite variational inequalities and establish improved convergence guarantees.
arXiv Detail & Related papers (2026-02-09T20:13:36Z) - Adaptive Differentially Quantized Subspace Perturbation (ADQSP): A Unified Framework for Privacy-Preserving Distributed Average Consensus [6.364764301218972]
We propose a general approach named adaptive differentially quantized subspace (ADQSP)
We show that by varying a single quantization parameter the proposed method can vary between SMPC-type performances and DP-type performances.
Our results show the potential of exploiting traditional distributed signal processing tools for providing cryptographic guarantees.
arXiv Detail & Related papers (2023-12-13T07:52:16Z) - Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences.
Our method is especially suitable for problems with well-specified likelihoods.
We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
arXiv Detail & Related papers (2023-11-08T00:10:21Z) - Bounded and Unbiased Composite Differential Privacy [25.427802467876248]
The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between two neighboring databases.
Existing solutions attempt to address this issue by employing post-processing or truncation techniques.
We propose a novel differentially private mechanism which uses a composite probability density function to generate bounded and unbiased outputs.
arXiv Detail & Related papers (2023-11-04T04:43:47Z) - Private Networked Federated Learning for Nonsmooth Objectives [7.278228169713637]
This paper develops a networked federated learning algorithm to solve nonsmooth objective functions.
We use the zero-concentrated differential privacy notion (zCDP) to guarantee the confidentiality of the participants.
We provide complete theoretical proof for the privacy guarantees and the algorithm's convergence to the exact solution.
arXiv Detail & Related papers (2023-06-24T16:13:28Z) - Theoretically Principled Federated Learning for Balancing Privacy and
Utility [61.03993520243198]
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters.
It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning.
arXiv Detail & Related papers (2023-05-24T13:44:02Z) - Differentially Private Decentralized Optimization with Relay Communication [1.2695958417031445]
We introduce a new measure: Privacy Leakage Frequency (PLF), which reveals the relationship between communication and privacy leakage of algorithms.
A novel differentially private decentralized primal--dual algorithm named DP-RECAL is proposed to take advantage of operator splitting method and relay communication mechanism to experience less PLF.
arXiv Detail & Related papers (2022-12-21T09:05:36Z) - Quantization enabled Privacy Protection in Decentralized Stochastic
Optimization [34.24521534464185]
Decentralized optimization can be used in areas as diverse as machine learning, control, and sensor networks.
Privacy protection has emerged as a crucial need in the implementation of decentralized optimization.
We propose an algorithm that is able to guarantee provable convergence accuracy even in the presence of aggressive quantization errors.
arXiv Detail & Related papers (2022-08-07T15:17:23Z) - Tree ensemble kernels for Bayesian optimization with known constraints
over mixed-feature spaces [54.58348769621782]
Tree ensembles can be well-suited for black-box optimization tasks such as algorithm tuning and neural architecture search.
Two well-known challenges in using tree ensembles for black-box optimization are (i) effectively quantifying model uncertainty for exploration and (ii) optimizing over the piece-wise constant acquisition function.
Our framework performs as well as state-of-the-art methods for unconstrained black-box optimization over continuous/discrete features and outperforms competing methods for problems combining mixed-variable feature spaces and known input constraints.
arXiv Detail & Related papers (2022-07-02T16:59:37Z) - Decentralized Stochastic Optimization with Inherent Privacy Protection [103.62463469366557]
Decentralized optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing.
Since involved data, privacy protection has become an increasingly pressing need in the implementation of decentralized optimization algorithms.
arXiv Detail & Related papers (2022-05-08T14:38:23Z) - An automatic differentiation system for the age of differential privacy [65.35244647521989]
Tritium is an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML)
We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML)
arXiv Detail & Related papers (2021-09-22T08:07:42Z) - Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth
Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO.
We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size.
Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
arXiv Detail & Related papers (2021-06-30T18:32:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.