Professor Jared Tanner

My research focus is on the design, analysis, and application of numerical algorithms for information inspired applications in signal and image processing.

Publications

Preprints

• Activation function design for deep networks: linearity and effective initialisation Michael Murray, Vinayak Abrol, and Jared Tanner.
• Compressed sensing of low-rank plus sparse matrices Jared Tanner and Simon Vary.
• The permuted striped block model and its factorization – algorithms with recovery guarantees Michael Murray and Jared Tanner.
• Trajectory growth lower bounds for random sparse deep ReLU networks Ilan Price and Jared Tanner.

Journal Articles

• An empirical study of derivative-free-optimization algorithms for targeted black-box attacks in deep neural networks Giuseppe Ughi, Vinayak Abrol, and Jared Tanner; Optimization and Engineering, accepted.
• Approximate message passing with a colored aliasing model for variable density Fourier sampled images Charles Millard, Aaron T Hess, Boris Mailhe, and Jared Tanner; IEEE Open Journal of Signal Processing, Vol. 1(1), (2020) 146-158.
• Geometric anomaly detection in data Bernadette J. Stolz, Jared Tanner, Heather A Harrington, and Vidit Nanda; Proceedings of the National Academy of Sciences, Vol. 117(33), (2020) 19664-19669.
• Sparse non-negative super-resolution — simplified and stabilised Armin Eftekhari, Jared Tanner, Andrew Thompson, Bogdan Toader, and Hemant Tyagi; Applied and Computational Harmonic Analysis, Vol. 50(1), (2021) 216-280.
• Matrix rigidity and the ill-posedness of Robust PCA and matrix completion Jared Tanner, Andrew Thompson, and Simon Vary; SIAM Mathematics of Data Science, Vol. 1(3) (2019) 537-554.
• On the construction of sparse matrices from expander graphs Bubacarr Bah and Jared Tanner; Frontiers in Applied Mathematics and Statistics (2018).
• A robust parallel algorithm for combinatorial compressed sensing Rodrigo Mendoza-Smith, Jared Tanner, and Florian Wechsung; IEEE Transactions on Signal Processing, Vol. 66(8) (2018) 2167-2177.
• Expander l0-decoding Rodrigo Mendoza-Smith and Jared Tanner; Applied and Computational Harmonic Analysis, Vol. 45(3) (2018) 642-667.
• Low rank matrix completion by alternating steepest descent methods Jared Tanner and Ke Wei; Applied and Computational Harmonic Analysis, Vol. 40(2) (2016) 417-429.
• CGIHT: Conjugate Gradient Iterative Hard Thresholding for compressed sensing and matrix completion Jeffrey D. Blanchard, Jared Tanner and Ke Wei; Information and Inference, Vol. 4(4) (2015) 289-327.
• Performance comparison of greedy algorithms in compressed sensing Jeffrey D. Blanchard and Jared Tanner; Numerical Linear Algebra with Applications, Vol. 22(2) (2015) 254-282.
• Conjugate Gradient Iterative Hard Thresholding: observed noise stability for compressed sensing Jeffrey D. Blanchard, Jared Tanner, and Ke Wei; IEEE Transactions on Signal Processing, Vol. 63(2) (2015) 528-537. Supplementary material.
• Bounds of restricted isometry constants in extreme asymptotics: formulae for Gaussian matrices Bubacarr Bah and Jared Tanner; Linear Algebra and its Applications, Vol. 441(1) (2014) 88-109.
• Normalized iterative hard thresholding for matrix completion Jared Tanner and Ke Wei; SIAM J. on Scientific Computing, Vol. 35(5) (2013) S104-S125.
• Vanishingly sparse matrices and expander graphs, with application to compressed sensing Bubacarr Bah and Jared Tanner; IEEE Transactions on Information Theory, Vol. 59(11) (2013) 7491-7508.
• GPU accelerated greedy algorithms for compressed sensing Jeffrey D. Blanchard and Jared Tanner; Mathematical Programming Computation, Vol. 5(3) (2013) 267-304. Website for the associated software.
• Improved bounds on restricted isometry constants for Gaussian matrices, Bubacarr Bah and Jared Tanner; SIAM Journal on Matrix Analysis , Vol. 31(5) (2010) 2882-2898.
• Coarse quantization for random interleaved sampling of bandlimited signals, Alexander M. Powell, Jared Tanner, Yang Wang, and Ozgur Yilmaz; Mathematical Modelling and Numerical Analysis, Vol. 46(3) (2012) 605-618.
• Phase transitions for greedy sparse approximation algorithms, Jeffrey D. Blanchard, Coralia Cartis, Jared Tanner, and Andrew Thompson; Applied and Computational Harmonic Analysis, Vol. 30(2) (2011) 188-203.
• Precise Undersampling Theorems, David L. Donoho and Jared Tanner; Proceedings of the IEEE, Vol. 98(6), (2010), 913-924.
• Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing, David L. Donoho and Jared Tanner; Philosophical Transactions of the Royal Society A, Vol. 367(1906), (2009) 4273–4293.
• Decay properties for restricted isometry constants, Jeffrey D. Blanchard, Coralia Cartis, and Jared Tanner; IEEE Signal Processing Letters, Vol. 16(7), (2009) 572–575.
• Compressed Sensing: How sharp is the Restricted Isometry Property?, Jeffrey D. Blanchard, Coralia Cartis, and Jared Tanner; SIAM Review, Vol. 53(1), (2011), 105-125.
• Counting the faces of randomly-projected hypercubes and orthants, with applications, David L. Donoho and Jared Tanner; Discrete and Computational Geometry, Vol. 43(3), (2010), 522-541.
• Exponential bounds implying construction of compressed sensing matrices, error-correcting codes and neighborly polytopes by random sampling, David L. Donoho and Jared Tanner; IEEE Transactions on Information Theory, Vol. 56(4), (2010), 2002-2016.
• Identification of Matrices having a Sparse Representation, Gotz E. Pfander, Holger Rauhut, and Jared Tanner;IEEE Transactions on Signal Processing, Vol. 56(11), (2008) 5376–5388.
• Counting faces of randomly-projected polytopes when the projection radically lowers dimension, David L. Donoho and Jared Tanner; Journal of the AMS, Vol. 22(1), (2009) 1–53.
• Neighborliness of Randomly-Projected Simplices in High Dimensions, David L. Donoho and Jared Tanner; Proceedings of the National Academy of Sciences, Vol. 102(27), (2005) 9452–9457.
• Sparse Nonnegative Solutions of Underdetermined Linear Equations by Linear Programming, David L. Donoho and Jared Tanner; Proceedings of the National Academy of Sciences, Vol. 102(27), (2005) 9446–9451.
• Robust reprojection methods for the resolution of Gibbs phenomenon, Anne Gelb and Jared Tanner; Applied and Computational Harmonic Analysis, Vol. 20(1) (2006) 3-25.
• Fast reconstruction methods for bandlimited functions from periodic nonuniform sampling, Thomas Strohmer and Jared Tanner; SIAM J. on Numerical Analysis, Vol. 44(3) (2006) 1073-1094.
• Optimal Filter and Mollifier for Piecewise Smooth Spectral Data, Jared Tanner; Mathematics of Computation, Vol. 75(254) (2006) 767-790.
• Adaptive Filters for Piecewise Smooth Spectral Data, Eitan Tadmor and Jared Tanner; IMA Journal of Numerical Analysis, Vol. 25(4) (2005) 635-647.
• Implementations of Shannon’s sampling theorem, a time-frequency approach, Thomas Strohmer and Jared Tanner; Sampling Theory in Signal and Image Processing, Vol. 4(1) (2005) 1-17.
• Adaptive Mollifiers – High Resolution Recover of Piecewise Smooth Data from its Spectral Information, Eitan Tadmor and Jared Tanner; Foundations of Computational Mathematics 2(2) (2002) 155-189.

Conference Proceedings

• Dense for the price of sparse: improved performance of sparsely initialized networks via a subspace offset Ilan Price and Jared Tanner; International Conference on Machine Learning (ICML), July 2021.
• Mutual information of neural network initializations: mean field approximations Jared Tanner and Giuseppe Ughi; IEEE International Symposium on Information Theory (ISIT), July 2021.
• An approximate message passing algorithm for rapid parameter-free compressed sensing MRI Charles Millard, Aaron T Hess, Boris Mailhe, and Jared Tanner; IEEE International Conference on Image Processing, October 2020.
• Information-Bottleneck under mean filed initialization Vinayak Abrol and Jared Tanner; ICML 2020 workshop: uncertainty and robustness in deep learning, July 2020.
• Multispectral Snapshot Demosaicing via Non-Convex Matrix Completion Giancarlo A. Antonucci, Simon Vary, David Humphreys, Robert A. Lamb, Jonathan Piper, and Jared Tanner; IEEE Data Science Workshop, Univ. of Minnesota, June 2019.
• Deep CNN sparse coding analysis: towards average case Michael Murray and Jared Tanner; IEEE Data Science Workshop, EPFL, June 2018.
• Non-negative super-resolution is stable Armin Eftekhari, Jared Tanner, Andrew Thompson, Bogdan Toader, and Hemant Tyagi; IEEE Data Science Workshop, EPFL, June 2018.
• Parallel multi-scale reduction of persistent homology filtrations Rodrigo Mendoza-Smith and Jared Tanner; NeurIPS 2017 workshop: synergies in geometric data analysis, December 2017.
• Phase transitions for restricted isometry properties, Jeffrey D. Blanchard, Coralia Cartis, and Jared Tanner; Proc. of SPARS’09 (Signal Processing with Adaptive Sparse Structured Representations), Saint-Malo (F), April 2009.
• Fast reconstruction algorithms for periodic nonuniform sampling with applications to time-interleaved ADCs, Thomas Strohmer and Jared Tanner; Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, April 2007.
• Thresholds for the Recovery of Sparse Solutions via L1 Minimization, David L. Donoho and Jared Tanner; Proceedings of the Conference on Information Sciences and Systems, March 2006.
• An Adaptive Order Godunov Type Central Scheme, Eitan Tadmor and Jared Tanner; “Hyperbolic Problems: Theory, Numerics, Applications”, Proceedings of the 9th International Conference in Pasadena, March 2002 (T. Hou and E. Tadmor, eds.), Springer, 2003, 871-880.

To view Professor Tanner’s departmental web page click here.