activity
20132021
most citedOn instabilities of deep learning in image reconstruction - Does AI come at a cost?

795 citations · 1.2k across the 12 of their papers we have counts for

collaborators
Showing cs.ITShow all

9 papers · 1 filter

cs.IT2016★ 23 cited

Bounds on the Number of Measurements for Reliable Compressive Classification

Hugo Reboredo, Francesco Renna, Robert Calderbank +1

This paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient cond…

cs.IT2015★ 3 cited

Mismatch in the Classification of Linear Subspaces: Sufficient Conditions for Reliable Classification

Jure Sokolic, Francesco Renna, Robert Calderbank +1

This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Ga…

cs.IT2014★ 48 cited

Classification and Reconstruction of High-Dimensional Signals from Low-Dimensional Features in the Presence of Side Information

Francesco Renna, Liming Wang, Xin Yuan +5

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 si…

cs.IT2014

Achievable Secrecy Rates over MIMOME Gaussian Channels with GMM Signals in Low-Noise Regime

Francesco Renna, Nicola Laurenti, Stefano Tomasin

We consider a wiretap multiple-input multiple-output multiple-eavesdropper (MIMOME) channel, where agent Alice aims at transmitting a secret message to agent Bob, while leaking no…

cs.IT2014★ 14 cited

Compressive Classification of a Mixture of Gaussians: Analysis, Designs and Geometrical Interpretation

Hugo Reboredo, Francesco Renna, Robert Calderbank +1

This paper derives fundamental limits on the performance of compressive classification when the source is a mixture of Gaussians. It provides an asymptotic analysis of a Bhattachar…

cs.IT2013★ 51 cited

Reconstruction of Signals Drawn from a Gaussian Mixture from Noisy Compressive Measurements

Francesco Renna, Robert Calderbank, Lawrence Carin +1

This paper determines to within a single measurement the minimum number of measurements required to successfully reconstruct a signal drawn from a Gaussian mixture model in the low…

cs.IT2013★ 1 cited

Secrecy Transmission on Block Fading Channels: Theoretical Limits and Performance of Practical Codes

Marco Baldi, Marco Bianchi, Franco Chiaraluce +3

We consider a system where an agent (Alice) aims at transmitting a message to a second agent (Bob) over a set of parallel channels, while keeping it secret from a third agent (Eve)…

cs.IT2013

Low-power Secret-key Agreement over OFDM

Francesco Renna, Nicola Laurenti, Stefano Tomasin +5

Information-theoretic secret-key agreement is perhaps the most practically feasible mechanism that provides unconditional security at the physical layer to date. In this paper, we…

cs.IT2013

Compressive Classification

Hugo Reboredo, Francesco Renna, Robert Calderbank +1

This paper derives fundamental limits associated with compressive classification of Gaussian mixture source models. In particular, we offer an asymptotic characterization of the be…