Browsing by Subject "Distributed estimation"

Now showing 1 - 7 of 7

Open Access
Communication efficient distributed estimation
(IEEE, 2016) Utlu, İhsan; Kozat, Süleyman Serdar
In this paper, we consider the problem of distributed estimation over adaptive networks with reduced load on communication resources. Novel diffusion strategies are presented that achieve up to three orders-of-magnitude reduction in the communication load on the network, while matching the state-of-the-art in performance. Specifically, the information transfer between the nodes of the network is conditioned on the level-crossings of the diffused parameter. We perform the mean stability analysis of the proposed algorithm, and provide numerical examples to verify the theoretical results.
Open Access
Distributed adaptive filtering with reduced communication load
(IEEE, 2016) Utlu, İhsan; Kozat, Süleyman Serdar
We propose novel algorithms for distributed processing in applications constrained by available communication resources, using diffusion strategies that achieve up to three orders-of-magnitude reduction in communication load on the network, while delivering equal performance with respect to the state of the art. After computation of local estimates, the information is diffused among processing elements (or nodes) non-uniformly in time by conditioning the information transfer on level-crossings of the diffused parameter, resulting in a greatly reduced communication requirement. We provide the mean stability analysis of our algorithms, and illustrate the gain in communication efficiency compared to other reducedcommunication distributed estimation schemes.
Open Access
Efficient learning strategies over distributed networks for big data
(2017-07) Kılıç, Osman Fatih
We study the problem of online learning over a distributed network, where agents in the network collaboratively estimate an underlying parameter of interest using noisy observations. For the applicability of such systems, sustaining a communication and computation efficiency while providing a comparable performance plays a crucial role. To this end, in this work, we propose computation and communication wise highly efficient distributed online learning methods that present superior performance compared to the state-of-the-art. In the first part of the thesis, we study distributed centralized estimation schemes, where such approaches require high communication bandwidth and high computational load. We introduce a novel approach based on set-membership filtering to reduce such burdens of the system. In the second part of our work, we study distributed decentralized estimation schemes, where nodes in the network individually and collaboratively estimate a dynamically evolving parameter using noisy observations. We present an optimal decentralized learning algorithm through disclosure of local estimates and prove that optimal estimation in such systems is possible only over certain network topologies. We then derive an iterative algorithm to recursively construct the optimal combination weights and the estimation. Through series of simulations over generated and real-life benchmark data, we demonstrate the superior performance of the proposed methods compared to state-of-the-art distributed learning methods. We show that the introduced algorithms provide improved learning rates and lower steady-state error levels while requiring much less communication and computation load on the system.
Open Access
Event-triggered distributed estimation with reduced communication load
(2017-01) Utlu, İhsan
We propose a novel algorithm for distributed processing applications constrained by the available communication resources using diffusion strategies that achieves up to a 103 fold reduction in the communication load over the network, while delivering a comparable performance with respect to the state of the art. After the computation of the local estimates, the information is diffused among the processing elements (or nodes) non-uniformly in time by conditioning the information transfer on level-crossings of the diffused parameter, resulting in a greatly reduced communication requirement. We provide the mean and meansquare stability analyses of the proposed algorithm, and illustrate the gain in communication efficiency compared to other reduced-communication distributed estimation schemes.
Open Access
Logarithmic regret bound over diffusion based distributed estimation
(IEEE, 2014) Sayın, Muhammed O.; Vanlı, Nuri Denizcan; Kozat, Süleyman Serdar
We provide a logarithmic upper-bound on the regret function of the diffusion implementation for the distributed estimation. For certain learning rates, the bound shows guaranteed performance convergence of the distributed least mean square (DLMS) algorithms to the performance of the best estimation generated with hindsight of spatial and temporal data. We use a new cost definition for distributed estimation based on the widely-used statistical performance measures and the corresponding global regret function. Then, for certain learning rates, we provide an upper-bound on the global regret function without any statistical assumptions.
Open Access
Resource-aware event triggered distributed estimation over adaptive networks
(Elsevier Inc., 2017) Utlu, I.; Kilic, O. F.; Kozat S. S.
We propose a novel algorithm for distributed processing applications constrained by the available communication resources using diffusion strategies that achieves up to a 103 fold reduction in the communication load over the network, while delivering a comparable performance with respect to the state of the art. After computation of local estimates, the information is diffused among the processing elements (or nodes) non-uniformly in time by conditioning the information transfer on level-crossings of the diffused parameter, resulting in a greatly reduced communication requirement. We provide the mean and mean-square stability analyses of our algorithms, and illustrate the gain in communication efficiency compared to other reduced-communication distributed estimation schemes.
Open Access
Signal recovery with cost-constrained measurements
(IEE, 2010-03-22) Özçelikkale, A.; Özaktaş, Haldun M.; Arikan, E.
We are concerned with the problem of optimally measuring an accessible signal under a total cost constraint, in order to estimate a signal which is not directly accessible. An important aspect of our formulation is the inclusion of a measurement device model where each device has a cost depending on the number of amplitude levels that the device can reliably distinguish. We also assume that there is a cost budget so that it is not possible to make a high amplitude resolution measurement at every point. We investigate the optimal allocation of cost budget to the measurement devices so as to minimize estimation error. This problem differs from standard estimation problems in that we are allowed to design the number and noise levels of the measurement devices subject to the cost constraint. Our main results are presented in the form of tradeoff curves between the estimation error and the cost budget. Although our primary motivation and numerical examples come from wave propagation problems, our formulation is also valid for other measurement problems with similar budget limitations where the observed variables are related to the unknown variables through a linear relation. We discuss the effects of signal-to-noise ratio, distance of propagation, and the degree of coherence (correlation) of the waves on these tradeoffs and the optimum cost allocation. Our conclusions not only yield practical strategies for designing optimal measurement systems under cost constraints, but also provide insights into measurement aspects of certain inverse problems.