A low-complexity universal scheme for rate-constrained distributed regression using a wireless sensor network

Authors:
Avon L. Fernandes;Maxim Raginsky;Todd P. Coleman
Affiliations:
Microsoft Corporation, Redmond, WA and Department of Electrical and Computer Engineering, University of Illinois, Urbana, IL;Department of Electrical and Computer Engineering, Duke University, Durham, NC and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana, IL;Department of Electrical and Computer Engineering, University of Illinois, Urbana, IL
Venue:
IEEE Transactions on Signal Processing
Year:
2009

Citing 14
Cited 0

Elements of information theory

Elements of information theory
Source Coding Theory

Source Coding Theory
Progressive meshes transmission over a wired-to-wireless network

Wireless Networks
A Learning-Theory Approach to Sensor Networks

IEEE Pervasive Computing
On the many-to-one transport capacity of a dense wireless sensor network and the compressibility of its data

IPSN'03 Proceedings of the 2nd international conference on Information processing in sensor networks
Relative location estimation in wireless sensor networks

IEEE Transactions on Signal Processing
Universal prediction

IEEE Transactions on Information Theory
Distributed source coding using syndromes (DISCUS): design and construction

IEEE Transactions on Information Theory
Decentralized estimation in an inhomogeneous sensing environment

IEEE Transactions on Information Theory
Consistency in models for distributed learning under communication constraints

IEEE Transactions on Information Theory
Lattice Quantization With Side Information: Codes, Asymptotics, and Applications in Sensor Networks

IEEE Transactions on Information Theory
Side information aware coding strategies for sensor networks

IEEE Journal on Selected Areas in Communications
Quantized incremental algorithms for distributed optimization

IEEE Journal on Selected Areas in Communications
Positioning in ad hoc sensor networks

IEEE Network: The Magazine of Global Internetworking

Quantified Score

Hi-index	35.68

Visualization

Abstract

We propose a scheme for rate-constrained distributed nonparametric regression using a wireless sensor network. The scheme is universal across a wide range of sensor noise models, including unbounded and nonadditive noise; it has low complexity, requiring simple operations such as uniform scalar quantization with dither and message passing between neighboring nodes in the network, and attains minimax optimality for regression functions in common smoothness classes. We present theoretical results on the tradeoff between the compression rate, communication complexity of encoding, and the MSE and demonstrate empirical performance of the scheme using simulations.