• Publications
  • Influence
On instabilities of deep learning in image reconstruction and the potential costs of AI
TLDR
In this paper, we demonstrate a crucial phenomenon: Deep learning typically yields unstable methods for image reconstruction with potential to change the field. Expand
  • 69
  • 6
  • PDF
Physical-Layer Secrecy for OFDM Transmissions Over Fading Channels
TLDR
This paper considers the information theoretic secrecy rates that are achievable by an orthogonal frequency-division multiplexing (OFDM) transmitter/receiver pair in the presence of an eavesdropper that might either use an OFDM structure or choose a more complex receiver architecture. Expand
  • 89
  • 5
Deep Convolutional Neural Networks for Heart Sound Segmentation
TLDR
This paper studies the use of deep convolutional neural networks to segment heart sounds into their main components. Expand
  • 12
  • 3
Moonlighting and overtime: A cross-country analysis
I investigate how contractual hours and overtime premiums affect the decision either to moonlight or to work overtime. By reducing the standard workweek, the government or labor unions can affect theExpand
  • 28
  • 3
Reconstruction of Signals Drawn From a Gaussian Mixture Via Noisy Compressive Measurements
TLDR
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-noise regime. Expand
  • 44
  • 2
  • PDF
Secrecy Transmission on Parallel Channels: Theoretical Limits and Performance of Practical Codes
TLDR
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) by using physical layer security techniques. Expand
  • 28
  • 2
Semi-Blind Key-Agreement over MIMO Fading Channels
TLDR
In this paper, we study the fundamental limits of secret-key agreement over MIMO quasi-static fading channels. Expand
  • 24
  • 2
  • PDF
Classification and Reconstruction of High-Dimensional Signals From Low-Dimensional Features in the Presence of Side Information
TLDR
This paper offers a principled framework that can be used not only to study fundamental limits in the classification and reconstruction of high-dimensional signals from low-dimensional signal features in the presence of side information, but also to obtain state-of-the-art results in imaging problems. Expand
  • 38
  • 1
  • PDF
Compressive Classification of a Mixture of Gaussians: Analysis, Designs and Geometrical Interpretation
TLDR
This paper derives fundamental limits on the performance of compressive classification when the source is a mixture of Gaussians. Expand
  • 16
  • 1
  • PDF
Achievable secrecy rates for wiretap OFDM with QAM constellations
TLDR
This paper considers the information theoretic secrecy rates that are achievable in a wiretap OFDM channel when transmitting quadrature amplitude modulation (QAM) constellation symbols. Expand
  • 9
  • 1