Neumann networks for linear inverse problems in imaging

D Gilton, G Ongie, R Willett - IEEE Transactions on …, 2019‏ - ieeexplore.ieee.org
Many challenging image processing tasks can be described by an ill-posed linear inverse
problem: deblurring, deconvolution, inpainting, compressed sensing, and superresolution all …

Sketching for large-scale learning of mixture models

N Keriven, A Bourrier, R Gribonval… - … and Inference: A …, 2018‏ - academic.oup.com
Learning parameters from voluminous data can be prohibitive in terms of memory and
computational requirements. We propose a 'compressive learning'framework, where we …

Multilinear compressive learning

DT Tran, M Yamaç, A Degerli… - IEEE transactions on …, 2020‏ - ieeexplore.ieee.org
Compressive learning (CL) is an emerging topic that combines signal acquisition via
compressive sensing (CS) and machine learning to perform inference tasks directly on a …

Classification and reconstruction of high-dimensional signals from low-dimensional features in the presence of side information

F Renna, L Wang, X Yuan, J Yang… - IEEE Transactions …, 2016‏ - ieeexplore.ieee.org
This paper offers a characterization of fundamental limits on the classification and
reconstruction of high-dimensional signals from low-dimensional features, in the presence of …

Reconstruction of signals drawn from a Gaussian mixture via noisy compressive measurements

F Renna, R Calderbank, L Carin… - IEEE Transactions on …, 2014‏ - ieeexplore.ieee.org
This paper determines to within a single measurement the minimum number of
measurements required to successfully reconstruct a signal drawn from a Gaussian mixture …

Bounds on the number of measurements for reliable compressive classification

H Reboredo, F Renna, R Calderbank… - IEEE Transactions …, 2016‏ - ieeexplore.ieee.org
This paper studies the classification of high-dimensional Gaussian signals from low-
dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient …

Compressive detection of random subspace signals

A Razavi, M Valkama, D Cabric - IEEE Transactions on Signal …, 2016‏ - ieeexplore.ieee.org
The problem of compressive detection of random subspace signals is studied. We consider
signals modeled as s= Hx where H is an N× K matrix with K≤ N and x~ N (0 K, 1, σ∞ 2 IK) …

Selective CS: An energy-efficient sensing architecture for wireless implantable neural decoding

C Song, A Wang, F Lin, J **ao, X Yao… - IEEE Journal on …, 2018‏ - ieeexplore.ieee.org
The spike classification is a critical step in the implantable neural decoding. The energy
efficiency issue in the sensor node is a big challenge for the entire system. Compressive …

Performance bounds of compressive classification under perturbation

Y Cui, W Xu, Y Wang, J Lin, L Lu - Signal Processing, 2021‏ - Elsevier
Recently, compressive sensing based classification, which is called compressive
classification, has drawn a lot of attention, since it works directly in the compressive domain …

Projections designs for compressive classification

H Reboredo, F Renna, R Calderbank… - 2013 IEEE Global …, 2013‏ - ieeexplore.ieee.org
This paper puts forth projections designs for compressive classification of Gaussian mixture
models. In particular, we capitalize on the asymptotic characterization of the behavior of an …