15 citations · 52 across the 16 of their papers we have counts for
16 papers
SAND: One-Shot Feature Selection with Additive Noise Distortion
Pedram Pad, Hadi Hammoud, Mohamad Dia +2
Feature selection is a critical step in data-driven applications, reducing input dimensionality to enhance learning accuracy, computational efficiency, and interpretability. Existi…
PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
Yamin Sepehri, Pedram Pad, Pascal Frossard +1
The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training d…
Hierarchical Training of Deep Neural Networks Using Early Exiting
Yamin Sepehri, Pedram Pad, Ahmet Caner Yüzügüler +2
Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the ed…
Privacy-Preserving Image Acquisition Using Trainable Optical Kernel
Yamin Sepehri, Pedram Pad, Pascal Frossard +1
Preserving privacy is a growing concern in our society where sensors and cameras are ubiquitous. In this work, for the first time, we propose a trainable image acquisition method t…
Optimality of Operator-Like Wavelets for Representing Sparse AR(1) Processes
Pedram Pad, Michael Unser
It is known that the Karhunen-Loève transform (KLT) of Gaussian first-order auto-regressive (AR(1)) processes results in sinusoidal basis functions. The same sinusoidal bases come…
New Power Estimation Methods for Highly Overloaded Synchronous CDMA Systems
Damoun Nashtaali, Omid Mashayekhi, Pedram Pad +2
In CDMA systems, the received user powers vary due to moving distance of users. Thus, the CDMA receivers consist of two stages. The first stage is the power estimator and the secon…