42 citations · 133 across the 18 of their papers we have counts for
24 papers
Inverse Constrained Reinforcement Learning
Usman Anwar, Shehryar Malik, Alireza Aghasi +1
In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is crit…
Subsampled Fourier Ptychography using Pretrained Invertible and Untrained Network Priors
Fahad Shamshad, Asif Hanif, Ali Ahmed
Recently pretrained generative models have shown promising results for subsampled Fourier Ptychography (FP) in terms of quality of reconstruction for extremely low sampling rate an…
Learning To Solve Differential Equations Across Initial Conditions
Shehryar Malik, Usman Anwar, Ali Ahmed +1
Recently, there has been a lot of interest in using neural networks for solving partial differential equations. A number of neural network-based partial differential equation solve…
Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior
Fahad Shamshad, Ali Ahmed
In this paper, we consider the highly ill-posed problem of jointly recovering two real-valued signals from the phaseless measurements of their circular convolution. The problem ari…
Sub-Nyquist Sampling of Sparse and Correlated Signals in Array Processing
Ali Ahmed, Fahad Shamshad, Humera Hameed
This paper considers efficient sampling of simultaneously sparse and correlated (SC) signals. Such signals arise in various applications in array processing. We propose an impl…
Blind Image Deconvolution using Pretrained Generative Priors
Muhammad Asim, Fahad Shamshad, Ali Ahmed
This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate d…
Bilinear Compressed Sensing under known Signs via Convex Programming
Alireza Aghasi, Ali Ahmed, Paul Hand +1
We consider the bilinear inverse problem of recovering two vectors, and , from their entrywise product. We consider…
Simultaneous Phase Retrieval and Blind Deconvolution via Convex Programming
Ali Ahmed, Alireza Aghasi, Paul Hand
We consider the task of recovering two real or complex -vectors from phaseless Fourier measurements of their circular convolution. Our method is a novel convex relaxation that i…
Invertible generative models for inverse problems: mitigating representation error and dataset bias
Muhammad Asim, Mara Daniels, Oscar Leong +2
Trained generative models have shown remarkable performance as priors for inverse problems in imaging -- for example, Generative Adversarial Network priors permit recovery of test…
Channel Protection using Random Modulation
Ali Ahmed, Humera Hameed
This paper shows that modulation protects a bandlimited signal against convolutive interference. A signal , bandlimited to Hz, is modulated (pointwise multiplied) with a k…
Deep Ptych: Subsampled Fourier Ptychography using Generative Priors
Fahad Shamshad, Farwa Abbas, Ali Ahmed
This paper proposes a novel framework to regularize the highly ill-posed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our…
Leveraging Deep Stein's Unbiased Risk Estimator for Unsupervised X-ray Denoising
Fahad Shamshad, Muhammad Awais, Muhammad Asim +3
Among the plethora of techniques devised to curb the prevalence of noise in medical images, deep learning based approaches have shown the most promise. However, one critical limita…
Blind Deconvolution using Modulated Inputs
Ali Ahmed
This paper considers the blind deconvolution of multiple modulated signals, and an arbitrary filter. Multiple inputs $\boldsymbol{s}_1, \boldsymbol{s}_2, \ldots, \boldsymbol{s}_N =…
A convex program for bilinear inversion of sparse vectors
Alireza Aghasi, Ali Ahmed, Paul Hand +1
We consider the bilinear inverse problem of recovering two vectors, and , from their entrywise product. We consider t…
Robust Compressive Phase Retrieval via Deep Generative Priors
Fahad Shamshad, Ali Ahmed
This paper proposes a new framework to regularize the highly ill-posed and non-linear phase retrieval problem through deep generative priors using simple gradient descent algorithm…
Blind Deconvolutional Phase Retrieval via Convex Programming
Ali Ahmed, Alireza Aghasi, Paul Hand
We consider the task of recovering two real or complex -vectors from phaseless Fourier measurements of their circular convolution. Our method is a novel convex relaxation that i…
Blind Image Deconvolution using Deep Generative Priors
Muhammad Asim, Fahad Shamshad, Ali Ahmed
This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as pri…
BranchHull: Convex bilinear inversion from the entrywise product of signals with known signs
Alireza Aghasi, Ali Ahmed, Paul Hand +1
We consider the bilinear inverse problem of recovering two vectors, and , in from their entrywise product. For the case where the vectors have known signs and…
A Convex Program for Mixed Linear Regression with a Recovery Guarantee for Well-Separated Data
Paul Hand, Babhru Joshi
We introduce a convex approach for mixed linear regression over features. This approach is a second-order cone program, based on L1 minimization, which assigns an estimate regr…
Leveraging Diversity and Sparsity in Blind Deconvolution
Ali Ahmed, Laurent Demanet
This paper considers recovering -dimensional vectors , and from their circular convolutions $\bolds…
Empirical Chaos Processes and Blind Deconvolution
Ali Ahmed, Felix Krahmer, Justin Romberg
This paper investigates conditions under which certain kinds of systems of bilinear equations have a unique structured solution. In particular, we look at when we can recover vecto…
Compressive Sampling of Ensembles of Correlated Signals
Ali Ahmed, Justin Romberg
We propose several sampling architectures for the efficient acquisition of an ensemble of correlated signals. We show that without prior knowledge of the correlation structure, eac…
Compressive Multiplexing of Correlated Signals
Ali Ahmed, Justin Romberg
We present a general architecture for the acquisition of ensembles of correlated signals. The signals are multiplexed onto a single line by mixing each one against a different code…
Blind Deconvolution using Convex Programming
Ali Ahmed, Benjamin Recht, Justin Romberg
We consider the problem of recovering two unknown vectors, and , of length from their circular convolution. We make the structural assumption t…