检索结果-内蒙古大学图书馆

Differentially Private Online Federated Learning with Correlated Noise

学校读者我要写书评

暂无评论

Differentially Private Online Federated Learning with Correl...

IEEE Conference on Decision and control

作者： Jiaojiao Zhang Linglingzhi Zhu Mikael Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Systems Engineering and Engineering Management Chinese University of Hong Kong

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an $(\epsilon, \delta)$ DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm.

关键词： Privacy Federated learning Heuristic algorithms Noise Signal processing algorithms Servers

Online Traffic Density Estimation using Physics-Informed Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wilkman, Dennis Morozovska, Kateryna Johansson, Karl Henrik Barreau, Matthieu Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology 100-44 Sweden

Recent works on the application of Physics-Informed Neural Networks to traffic density estimation have shown to be promising for future developments due to their robustness to model errors and noisy data. In this paper, we introduce a methodology for online approximation of the traffic density using measurements from probe vehicles in two settings: one using the Greenshield model and the other considering a high-fidelity traffic simulation. The proposed method continuously estimates the real-time traffic density in space and performs model identification with each new set of measurements. The density estimate is updated in almost real-time using gradient descent and adaptive weights. In the case of full model knowledge, the resulting algorithm has similar performance to the classical open-loop one. However, in the case of model mismatch, the iterative solution behaves as a closed-loop observer and outperforms the baseline method. Similarly, in the high-fidelity setting, the proposed algorithm correctly reproduces the traffic characteristics. Copyright © 2025, The Authors. All rights reserved.

关键词：

Bayes and Biased Estimators Without Hyper-parameter Estimation: Comparable Performance to the Empirical-Bayes-Based Regularized Estimator

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ju, Yue Wahlberg, Bo Hjalmarsson, Håkan Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

Regularized system identification has become a significant complement to more classical system identification. It has been numerically shown that kernel-based regularized estimators often perform better than the maximum likelihood estimator in terms of minimizing mean squared error (MSE). However, regularized estimators often require hyper-parameter estimation. This paper focuses on ridge regression and the regularized estimator by employing the empirical Bayes hyperparameter estimator. We utilize the excess MSE to quantify the MSE difference between the empirical-Bayes-based regularized estimator and the maximum likelihood estimator for large sample sizes. We then exploit the excess MSE expressions to develop both a family of generalized Bayes estimators and a family of closed-form biased estimators. They have the same excess MSE as the empirical-Bayes-based regularized estimator but eliminate the need for hyper-parameter estimation. Moreover, we conduct numerical simulations to show that the performance of these new estimators is comparable to the empirical-Bayes-based regularized estimator, while computationally, they are more efficient. Copyright © 2025, The Authors. All rights reserved.

关键词： Mean square error

Risk-Averse Learning with Delayed feedback

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

In real-world scenarios, the impacts of decisions may not manifest immediately. Taking these delays into account facilitates accurate assessment and management of risk in real-world environments, thereby ensuring the efficacy of strategies. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating delayed feedback with unknown but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The regret achieved by the algorithms is analyzed in terms of the cumulative delay and the number of total samplings. The results suggest that the two-point risk-averse learning achieves a smaller regret bound than the one-point algorithm. Furthermore, the one-point risk-averse learning algorithm attains sublinear regret under certain delay conditions, and the two-point risk-averse learning algorithm achieves sublinear regret with minimal restrictions on the delay. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the proposed algorithms. © 2024, CC0.

关键词： Adversarial machine learning

Model-Plant Mismatch Detection Using the Plant-Model Ratio: The Influence of Multivariable systems Containing Both Fast and Slow Dynamics.

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第25期58卷 55-60页

作者： Heinz K. Mittermaier Johan D. le Roux Ian K. Craig Measurement and Control Division Mintek Randburg South Africa Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria South Africa

The plant-model ratio, developed to diagnose model-plant mismatch present in model-based controllers, inherits the same limitations from the frequency-based analysis that the method is based on. Nonetheless, the plant-model ratio shows the capacity to counteract the effect of non-linear dynamics within processes due to the ability to diagnose parametric model-plant mismatches for first-order plus time delay models. The plant-model ratio is developed before being validated on the Wood-Berry distillation column. One of the prominent limitations of frequency analysis, the filtering effects of time constant differences, is investigated and quantified for the Wood-Berry distillation column, showing the effect of time constant differences on each parametric model-plant mismatch diagnosis.

关键词： controller performance monitoring grinding mill circuit model predictive control model-plant mismatch process performance monitoring

Real-time Hybrid System Identification with Online Deterministic Annealing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mavridis, Christos N. Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

We introduce a real-time identification method for discrete-time state-dependent switching systems in both the input-output and state-space domains. In particular, we design a system of adaptive algorithms running in two timescales;a stochastic approximation algorithm implements an online deterministic annealing scheme at a slow timescale and estimates the mode-switching signal, and an recursive identification algorithm runs at a faster timescale and updates the parameters of the local models based on the estimate of the switching signal. We first focus on piece-wise affine systems and discuss identifiability conditions and convergence properties based on the theory of two-timescale stochastic approximation. In contrast to standard identification algorithms for switched systems, the proposed approach gradually estimates the number of modes and is appropriate for real-time system identification using sequential data acquisition. The progressive nature of the algorithm improves computational efficiency and provides real-time control over the performance-complexity trade-off. Finally, we address specific challenges that arise in the application of the proposed methodology in identification of more general switching systems. Simulation results validate the efficacy of the proposed methodology. © 2024, CC BY.

关键词： Stochastic systems

Convex Equilibrium-Free Stability and Performance Analysis of Discrete-Time Nonlinear systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Koelewijn, Patrick J.W. Weiland, Siep Tóth, Roland Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Netherlands Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Hungary

This paper considers the equilibrium-free stability and performance analysis of discrete-time nonlinear systems. We consider two types of equilibrium-free notions. Namely, the universal shifted concept, which considers stability and performance w.r.t. all equilibrium points of the system, and the incremental concept, which considers stability and performance between trajectories of the system. In this paper, we show how universal shifted stability and performance of discrete-time systems can be analyzed by making use of the time-difference dynamics. Moreover, we extend the existing results for incremental dissipativity for discrete-time systems based on dissipativity analysis of the differential dynamics to more general state-dependent storage functions for less conservative results. Finally, we show how both these equilibrium-free notions can be cast as a convex analysis problem by making use of the linear parameter-varying framework, which is also demonstrated by means of an example. Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear systems

Slow Convergence of Interacting Kalman Filters in Word-of-Mouth Social Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Krishnamurthy, Vikram Rojas, Cristian R. School of Electrical and Computer Engineering Cornell University United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

We consider word-of-mouth social learning involving m Kalman filter agents that operate sequentially. The first Kalman filter receives the raw observations, while each subsequent Kalman filter receives a noisy measurement of the conditional mean of the previous Kalman filter. The prior is updated by the m-th Kalman filter. When m = 2, and the observations are noisy measurements of a Gaussian random variable, the covariance goes to zero as k−1/3 for k observations, instead of O(k−1) in the standard Kalman filter. In this paper we prove that for m agents, the covariance decreases to zero as k−(2m−1), i.e, the learning slows down exponentially with the number of agents. We also show that by artificially weighing the prior at each time, the learning rate can be made optimal as k−1. The implication is that in word-of-mouth social learning, artificially re-weighing the prior can yield the optimal learning rate. Copyright © 2024, The Authors. All rights reserved.

关键词： Kalman filters

Low-Complexity control for a Class of Uncertain MIMO Nonlinear systems under Generalized Time-Varying Output Constraints (extended version)

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mehdifar, Farhad Lindemann, Lars Bechlioulis, Charalampos P. Dimarogonas, Dimos V. Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Thomas Lord Department of Computer Science University of Southern California Los AngelesCA United States Division of Systems and Control Department of Electrical and Computer Engineering University of Patras Patra Greece

This paper introduces a novel control framework to address the satisfaction of multiple time-varying output constraints in uncertain high-order MIMO nonlinear control systems. Unlike existing methods, which often assume that the constraints are always decoupled and feasible, our approach can handle coupled time-varying constraints even in the presence of potential infeasibilities. First, it is shown that satisfying multiple constraints essentially boils down to ensuring the positivity of a scalar variable, representing the signed distance from the boundary of the time-varying output-constrained set. To achieve this, a single consolidating constraint is designed that, when satisfied, guarantees convergence to and invariance of the time-varying output-constrained set within a user-defined finite time. Next, a novel robust and low-complexity feedback controller is proposed to ensure the satisfaction of the consolidating constraint. Additionally, we provide a mechanism for online modification of the consolidating constraint to find a least violating solution when the constraints become mutually infeasible for some time. Finally, simulation examples of trajectory and region tracking for a mobile robot validate the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Feedback control