Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 44
-
ItemNo Preview AvailableAn Information-Theoretic Analysis for Transfer Learning: Error Bounds and Applications( 2022-07-12)Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis on the generalization error and excess risk of transfer learning algorithms, following a line of work initiated by Russo and Xu. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence D(μ||μ′) plays an important role in the characterizations where μ and μ′ denote the distribution of the training data and the testing test, respectively. Specifically, we provide generalization error upper bounds for the empirical risk minimization (ERM) algorithm where data from both distributions are available in the training phase. We further apply the analysis to approximated ERM methods such as the Gibbs algorithm and the stochastic gradient descent method. We then generalize the mutual information bound with ϕ-divergence and Wasserstein distance. These generalizations lead to tighter bounds and can handle the case when μ is not absolutely continuous with respect to μ′. Furthermore, we apply a new set of techniques to obtain an alternative upper bound which gives a fast (and optimal) learning rate for some learning problems. Finally, inspired by the derived bounds, we propose the InfoBoost algorithm in which the importance weights for source and target data are adjusted adaptively in accordance to information measures. The empirical results show the effectiveness of the proposed algorithm.
-
ItemAchieving QoS for Real-Time Bursty Applications over Passive Optical Networks( 2021-09-05)Emerging real-time applications such as those classified under ultra-reliable low latency (uRLLC) generate bursty traffic and have strict Quality of Service (QoS) requirements. Passive Optical Network (PON) is a popular access network technology, which is envisioned to handle such applications at the access segment of the network. However, the existing standards cannot handle strict QoS constraints. The available solutions rely on instantaneous heuristic decisions and maintain QoS constraints (mostly bandwidth) in an average sense. Existing works with optimal strategies are computationally complex and are not suitable for uRLLC applications. This paper presents a novel computationally-efficient, far-sighted bandwidth allocation policy design for facilitating bursty traffic in a PON framework while satisfying strict QoS (age of information/delay and bandwidth) requirements of modern applications. To this purpose, first we design a delay-tracking mechanism which allows us to model the resource allocation problem from a control-theoretic viewpoint as a Model Predictive Control (MPC). MPC helps in taking far-sighted decisions regarding resource allocations and captures the time-varying dynamics of the network. We provide computationally efficient polynomial-time solutions and show its implementation in the PON framework. Compared to existing approaches, MPC reduces delay violations by approximately 15% for a delay-constrained application of 1ms target. Our approach is also robust to varying traffic arrivals.
-
ItemAchieving AI-enabled Robust End-to-End Quality of Experience over Radio Access Networks( 2022-01-13)Emerging applications such as Augmented Reality, the Internet of Vehicles and Remote Surgery require both computing and networking functions working in harmony. The End-to-end (E2E) quality of experience (QoE) for these applications depends on the synchronous allocation of networking and computing resources. However, the relationship between the resources and the E2E QoE outcomes is typically stochastic and non-linear. In order to make efficient resource allocation decisions, it is essential to model these relationships. This article presents a novel machine-learning based approach to learn these relationships and concurrently orchestrate both resources for this purpose. The machine learning models further help make robust allocation decisions regarding stochastic variations and simplify robust optimization to a conventional constrained optimization. When resources are insufficient to accommodate all application requirements, our framework supports executing some of the applications with minimal degradation (graceful degradation) of E2E QoE. We also show how we can implement the learning and optimization methods in a distributed fashion by the Software-Defined Network (SDN) and Kubernetes technologies. Our results show that deep learning-based modelling achieves E2E QoE with approximately 99.8\% accuracy, and our robust joint-optimization technique allocates resources efficiently when compared to existing differential services alternatives.
-
Item
-
ItemMaximum-Hands-Off Control and L1 Optimality( 2013-07-31)In this article, we propose a new paradigm of control, called a maximum-hands-off control. A hands-off control is defined as a control that has a much shorter support than the horizon length. The maximum-hands-off control is the minimum-support (or sparsest) control among all admissible controls. We first prove that a solution to an L 1 -optimal control problem gives a maximum-handsoff control, and vice versa. This result rationalizes the use of L 1 optimality in computing a maximum-hands-off control. The solution has in general the ”bang-off-bang” property, and hence the control may be discontinuous. We then propose an L 1 /L 2 -optimal control to obtain a continuous hands-off control. Examples are shown to illustrate the effectiveness of the proposed control method.
-
ItemEvent-triggered transmission for linear control over communication channels( 2013-10-03)We consider an exponentially stable closed loop interconnection of a continuous linear plant and a continuous linear controller, and we study the problem of interconnecting the plant output to the controller input through a digital channel. We propose a family of “transmission-lazy” sensors whose goal is to transmit the measured plant output information as little as possible while preserving closed-loop stability. In particular, we propose two transmission policies, providing conditions on the transmission parameters. These guarantee global asymptotic stability when the plant state is available or when an estimate of the state is available (provided by a classical continuous linear observer). Moreover, under a specific condition, they guarantee global exponential stability.
-
ItemA Local Characterization of Lyapunov Functions and Robust Stability of Perturbed Systems on Riemannian Manifolds( 2013-10-31)This paper proposes converse Lyapunov theorems for nonlinear dynamical systems defined on smooth connected Riemannian manifolds and characterizes properties of Lyapunov functions with respect to the Riemannian distance function. We extend classical Lyapunov converse theorems for dynamical systems in R n to dynamical systems evolving on Riemannian manifolds. This is performed by restricting our analysis to the so called normal neighborhoods of equilibriums on Riemannian manifolds. By employing the derived properties of Lyapunov functions, we obtain the stability of perturbed dynamical systems on Riemannian manifolds.
-
ItemAveraging for nonlinear systems evolving on Riemannian manifolds( 2013-11-11)This paper presents an averaging method for nonlinear systems defined on Riemannian manifolds. We extend closeness of solutions results for ordinary differential equations on R n to dynamical systems defined on Riemannian manifolds by employing differential geometry. A generalization of closeness of solutions for periodic dynamical systems on compact time intervals is derived for dynamical systems evolving on compact Riemannian manifolds. Under local asymptotic (exponential) stability of the average vector field, we further relax the compactness of the ambient Riemannian manifold and obtain the closeness of solutions on the infinite time interval by employing the notion of uniform normal neighborhoods of an equilibrium point of a vector field. These results are also presented for time-varying dynamical systems where their averaged systems are almost globally asymptotically or exponentially stable on compact manifolds. The main results of the paper are illustrated by several examples.
-
ItemParameter and state estimation of nonlinear systems using a multi-observer under the supervisory framework( 2014-03-18)We present a hybrid scheme for the parameter and state estimation of nonlinear continuous-time systems, which is inspired by the supervisory setup used for control. State observers are synthesized for some nominal parameter values and a criterion is designed to select one of these observers at any given time instant, which provides state and parameter estimates. Assuming that a persistency of excitation condition holds, the convergence of the parameter and state estimation errors to zero is ensured up to a margin, which can be made as small as desired by increasing the number of observers. To reduce the potential computational complexity of the scheme, we explain how the sampling of the parameter set can be dynamically updated using a zoom-in procedure. This strategy typically requires a fewer number of observers for a given estimation error margin compared to the static sampling policy. The results are shown to be applicable to linear systems and to a class of nonlinear systems. We illustrate the applicability of the approach by estimating the synaptic gains and the mean membrane potentials of a neural mass model.
-
ItemHands-Off Control as Green Control( 2014-07-09)In this article, we introduce a new paradigm of control, called hands-off control, which can save energy and reduce CO2 emissions in control systems. A hands-off control is defined as a control that has a much shorter support than the horizon length. The maximum hands-off control is the minimum support (or sparsest) control among all admissible controls. With maximum hands-off control, actuators in the feedback control system can be stopped during time intervals over which the control values are zero. We show the maximum hands-off control is given by L 1 optimal control, for which we also show numerical computation formulas.
- 1 (current)
- 2
- 3
- 4
- 5