D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 31 Citations 37,494 114 World Ranking 7656 National Ranking 3585

Research.com Recognitions

Awards & Achievements

2021 - Jack S. Kilby Signal Processing Medal For groundbreaking contributions to compressed sensing.

2018 - IEEE Fellow For contributions to compressive sensing

Overview

What is he best known for?

The fields of study he is best known for:

  • Statistics
  • Algorithm
  • Artificial intelligence

His main research concerns Compressed sensing, Algorithm, Convex optimization, Signal reconstruction and Combinatorics. His research integrates issues of Probleme inverse, Orthogonal matrix and Iterative reconstruction, Computer vision in his study of Compressed sensing. His Algorithm study incorporates themes from Homotopy, Wavelet, Generalization error and Nonlinear system.

His Convex optimization research focuses on subjects like Data compression, which are linked to Image compression and Wavelet transform. His Combinatorics research includes themes of Discrete mathematics, Sign, Random matrix and Mathematical statistics. His studies deal with areas such as Fourier series and Piecewise as well as Free probability.

His most cited work include:

  • Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information (12980 citations)
  • Stable signal recovery from incomplete and inaccurate measurements (5850 citations)
  • Sparsity and incoherence in compressive sampling (1689 citations)

What are the main themes of his work throughout his whole career to date?

Justin Romberg focuses on Algorithm, Mathematical optimization, Compressed sensing, Convex optimization and Artificial intelligence. His study in Algorithm is interdisciplinary in nature, drawing from both Signal, Signal reconstruction, Signal processing and Communication channel. While the research belongs to areas of Compressed sensing, Justin Romberg spends his time largely on the problem of Bandwidth, intersecting his research to questions surrounding Mathematical analysis.

Justin Romberg has included themes like Linear matrix inequality, Combinatorics and Nonlinear system in his Convex optimization study. The concepts of his Combinatorics study are interwoven with issues in Discrete mathematics, Upper and lower bounds and Random matrix. His research in Artificial intelligence intersects with topics in Computer vision and Pattern recognition.

He most often published in these fields:

  • Algorithm (41.23%)
  • Mathematical optimization (21.05%)
  • Compressed sensing (18.86%)

What were the highlights of his more recent work (between 2019-2021)?

  • Reinforcement learning (6.58%)
  • Applied mathematics (8.77%)
  • Algorithm (41.23%)

In recent papers he was focusing on the following fields of study:

His primary areas of study are Reinforcement learning, Applied mathematics, Algorithm, Compressed sensing and Artificial neural network. His Reinforcement learning research incorporates themes from Mathematical optimization, Markov decision process, Markov process and Markov chain. His Applied mathematics study integrates concerns from other disciplines, such as Random matrix, Inverse problem, Blind deconvolution, Estimator and Series.

His Algorithm research is multidisciplinary, incorporating perspectives in Sampling and Array processing. Justin Romberg usually deals with Compressed sensing and limits it to topics linked to Regular polygon and Artificial intelligence. Within one scientific family, Justin Romberg focuses on topics pertaining to Computer hardware under Artificial neural network, and may sometimes address concerns connected to Shift register, Energy, Linear feedback shift register and Sparse matrix.

Between 2019 and 2021, his most popular works were:

  • STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence (9 citations)
  • Fast Convex Pruning of Deep Neural Networks (7 citations)
  • Convergence Rates of Distributed Gradient Methods Under Random Quantization: A Stochastic Approximation Approach (5 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Statistics
  • Algorithm

Justin Romberg mostly deals with Reinforcement learning, Applied mathematics, Artificial intelligence, Markov chain and Optimization problem. Reinforcement learning is closely attributed to Algorithm in his work. His Applied mathematics research is multidisciplinary, incorporating elements of Stochastic gradient descent, Markov process and Quantization.

His work on Range as part of general Artificial intelligence research is frequently linked to Baseline, bridging the gap between disciplines. His Markov chain research includes elements of Ergodic theory, Sampling, Sample and Trajectory. Justin Romberg has researched Optimization problem in several fields, including Point, Position and Control theory.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

E.J. Candes;J. Romberg;T. Tao.
IEEE Transactions on Information Theory (2006)

16660 Citations

Stable signal recovery from incomplete and inaccurate measurements

Emmanuel J. Candès;Justin K. Romberg;Terence Tao.
Communications on Pure and Applied Mathematics (2006)

7450 Citations

Sparsity and incoherence in compressive sampling

Emmanuel Candès;Justin Romberg.
Inverse Problems (2007)

2346 Citations

Imaging via Compressive Sampling

J. Romberg.
IEEE Signal Processing Magazine (2008)

1307 Citations

Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals

J.A. Tropp;J.N. Laska;M.F. Duarte;J.K. Romberg.
IEEE Transactions on Information Theory (2010)

1169 Citations

Quantitative Robust Uncertainty Principles and Optimally Sparse Decompositions

Emmanuel J. Candes;Justin Romberg.
Foundations of Computational Mathematics (2006)

656 Citations

Compressive Sensing by Random Convolution

Justin Romberg.
Siam Journal on Imaging Sciences (2009)

611 Citations

Practical Signal Recovery from Random Projections

Justin Romberg.
(2005)

457 Citations

Blind Deconvolution Using Convex Programming

Ali Ahmed;Benjamin Recht;Justin Romberg.
IEEE Transactions on Information Theory (2014)

346 Citations

Signal recovery from random projections

Emmanuel J. Candes;Justin K. Romberg.
electronic imaging (2005)

344 Citations

Best Scientists Citing Justin Romberg

Yonina C. Eldar

Yonina C. Eldar

Weizmann Institute of Science

Publications: 165

Richard G. Baraniuk

Richard G. Baraniuk

Rice University

Publications: 144

Michael B. Wakin

Michael B. Wakin

Colorado School of Mines

Publications: 91

Holger Rauhut

Holger Rauhut

RWTH Aachen University

Publications: 82

Emmanuel J. Candès

Emmanuel J. Candès

Stanford University

Publications: 76

Trac D. Tran

Trac D. Tran

Johns Hopkins University

Publications: 71

mike davies

mike davies

University of Edinburgh

Publications: 70

Felix J. Herrmann

Felix J. Herrmann

Georgia Institute of Technology

Publications: 67

Babak Hassibi

Babak Hassibi

California Institute of Technology

Publications: 67

Pierre Vandergheynst

Pierre Vandergheynst

École Polytechnique Fédérale de Lausanne

Publications: 64

Ge Wang

Ge Wang

Rensselaer Polytechnic Institute

Publications: 62

Marco F. Duarte

Marco F. Duarte

University of Massachusetts Amherst

Publications: 57

Guangming Shi

Guangming Shi

Xidian University

Publications: 56

Xin Yuan

Xin Yuan

Nanyang Technological University

Publications: 55

Yves Wiaux

Yves Wiaux

Heriot-Watt University

Publications: 54

Gonzalo R. Arce

Gonzalo R. Arce

University of Delaware

Publications: 54

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us
Something went wrong. Please try again later.