• Publications
  • Influence
Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems
TLDR
We propose gradient projection algorithms for the bound-constrained quadratic programming reformulation of a class of convex nonsmooth unconstrained optimization problems in signal processing and statistics. Expand
  • 2,953
  • 213
  • PDF
Generalized binary search
  • R. Nowak
  • Computer Science
  • 46th Annual Allerton Conference on Communication…
  • 1 September 2008
TLDR
This paper studies a generalization of the classic binary search problem of locating a desired value within a sorted list. Expand
  • 63
  • 16
  • PDF
Active learning for adaptive mobile sensing networks
TLDR
This paper investigates data-adaptive path planning schemes for wireless networks of mobile sensor platforms, in which previous samples are used to guide the motion of the mobiles for further sampling. Expand
  • 89
  • 10
  • PDF
Generalized likelihood ratio detection for fMRI using complex data
The majority of functional magnetic resonance imaging (fMRI) studies obtain functional information using statistical tests based on the magnitude image reconstructions. Recently, a complexExpand
  • 60
  • 8
  • PDF
Learning sparse doubly-selective channels
TLDR
In this paper, it is established that traditional training-based channel learning techniques are ill-suited to fully exploiting the inherent low-dimensionality of sparse channels. Expand
  • 80
  • 8
  • PDF
Compressive wireless sensing
TLDR
We propose a distributed matched source-channel communication scheme, based in part on recent results in compressive sampling theory, for estimation of sensed data at the fusion center and analyze, as a function of number of sensor nodes, the trade-offs between power, distortion and latency. Expand
  • 225
  • 7
  • PDF
Generalized consensus computation in networked systems with erasure links
TLDR
We study consensus problems in networked systems with unreliable links. Expand
  • 119
  • 6
  • PDF
Compressive Sampling for Signal Classification
TLDR
Compressive sampling (CS), also called compressed sensing, entails making observations of an unknown signal by projecting it onto random vectors. Expand
  • 116
  • 6
  • PDF
Decentralized compression and predistribution via randomized gossiping
TLDR
We present a novel system for decentralized data compression and predistribution in wireless sensor networks using a gossiping algorithm. Expand
  • 103
  • 5
  • PDF
Fast wavelet-based image deconvolution using the EM algorithm
TLDR
This paper introduces an expectation-maximization (EM) algorithm for image restoration (deconvolution) based on a penalized likelihood formulated in the wavelet domain. Expand
  • 71
  • 4
  • PDF