Search Results for author: Ali Ahmed

Found 14 papers, 4 papers with code

Constrained Reinforcement Learning With Learned Constraints

no code implementations1 Jan 2021 Shehryar Malik, Usman Anwar, Alireza Aghasi, Ali Ahmed

In this work, given a reward function and a set of demonstrations from an expert that maximizes this reward function while respecting \textit{unknown} constraints, we propose a framework to learn the most likely constraints that the expert respects.

reinforcement-learning

Inverse Constrained Reinforcement Learning

1 code implementation19 Nov 2020 Usman Anwar, Shehryar Malik, Alireza Aghasi, Ali Ahmed

However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely.

reinforcement-learning

Subsampled Fourier Ptychography using Pretrained Invertible and Untrained Network Priors

no code implementations13 May 2020 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 and high noise.

Learning To Solve Differential Equations Across Initial Conditions

no code implementations ICLR Workshop DeepDiffEq 2019 Shehryar Malik, Usman Anwar, Ali Ahmed, Alireza Aghasi

Recently, there has been a lot of interest in using neural networks for solving partial differential equations.

Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior

no code implementations28 Feb 2020 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.

Subsampled Fourier Ptychography via Pretrained Invertible and Untrained Network Priors

no code implementations NeurIPS Workshop Deep_Invers 2019 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 and high noise.

PatchDIP Exploiting Patch Redundancy in Deep Image Prior for Denoising

no code implementations NeurIPS Workshop Deep_Invers 2019 Muhammad Asim, Fahad Shamshad, Ali Ahmed

In this work, we show that this strong prior, enforced by the structure of a ConvNet, can be augmented with the information that recurs in different patches of a natural image to boost the performance.

Denoising

Blind Image Deconvolution using Pretrained Generative Priors

no code implementations20 Aug 2019 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.

Blind Image Deblurring Image Deblurring +1

Invertible generative models for inverse problems: mitigating representation error and dataset bias

1 code implementation28 May 2019 Muhammad Asim, Max Daniels, Oscar Leong, Ali Ahmed, Paul Hand

For compressive sensing, invertible priors can yield higher accuracy than sparsity priors across almost all undersampling ratios, and due to their lack of representation error, invertible priors can yield better reconstructions than GAN priors for images that have rare features of variation within the biased training set, including out-of-distribution natural images.

Compressive Sensing Denoising

Deep Ptych: Subsampled Fourier Ptychography using Generative Priors

no code implementations22 Dec 2018 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.

Leveraging Deep Stein's Unbiased Risk Estimator for Unsupervised X-ray Denoising

no code implementations29 Nov 2018 Fahad Shamshad, Muhammad Awais, Muhammad Asim, Zain ul Aabidin Lodhi, Muhammad Umair, Ali Ahmed

Among the plethora of techniques devised to curb the prevalence of noise in medical images, deep learning based approaches have shown the most promise.

Denoising

Robust Compressive Phase Retrieval via Deep Generative Priors

no code implementations17 Aug 2018 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.

Denoising

Blind Image Deconvolution using Deep Generative Priors

1 code implementation12 Feb 2018 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 priors.

Deblurring Image Deblurring +1

Blind Deconvolution using Convex Programming

1 code implementation21 Nov 2012 Ali Ahmed, Benjamin Recht, Justin Romberg

That is, we show that if $\boldsymbol{x}$ is drawn from a random subspace of dimension $N$, and $\boldsymbol{w}$ is a vector in a subspace of dimension $K$ whose basis vectors are "spread out" in the frequency domain, then nuclear norm minimization recovers $\boldsymbol{w}\boldsymbol{x}^*$ without error.

Information Theory Information Theory

Cannot find the paper you are looking for? You can Submit a new open access paper.