79 citations · 252 across the 9 of their papers we have counts for
9 papers
Denoising Diffusion Generative Models Secretly Calculate Attentions
Farzan Haddadi, Leila Monfared, Ebrahim Rezaii +3
Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer…
A Class of Nonconvex Penalties Preserving Overall Convexity in Optimization-Based Mean Filtering
Mohammadreza Malek-Mohammadi, Cristian R. Rojas, Bo Wahlberg
mean filtering is a conventional, optimization-based method to estimate the positions of jumps in a piecewise constant signal perturbed by additive noise. In this method,…
Successive Concave Sparsity Approximation for Compressed Sensing
Mohammadreza Malek-Mohammadi, Ali Koochakzadeh, Massoud Babaie-Zadeh +2
In this paper, based on a successively accuracy-increasing approximation of the norm, we propose a new algorithm for recovery of sparse vectors from underdetermined measur…
Iterative Concave Rank Approximation for Recovering Low-Rank Matrices
Mohammadreza Malek-Mohammadi, Massoud Babaie-Zadeh, Mikael Skoglund
In this paper, we propose a new algorithm for recovery of low-rank matrices from compressed linear measurements. The underlying idea of this algorithm is to closely approximate the…
Upper Bounds on the Error of Sparse Vector and Low-Rank Matrix Recovery
Mohammadreza Malek-Mohammadi, Cristian R. Rojas, Magnus Jansson +1
Suppose that a solution to an underdetermined linear system is given. is approximately sparse…
Performance Guarantees for Schatten- Quasi-Norm Minimization in Recovery of Low-Rank Matrices
Mohammadreza Malek-Mohammadi, Massoud Babaie-Zadeh, Mikael Skoglund
We address some theoretical guarantees for Schatten- quasi-norm minimization () in recovering low-rank matrices from compressed linear measurements. Firstly, using…
DOA Estimation in Partially Correlated Noise Using Low-Rank/Sparse Matrix Decomposition
Mohammadreza Malek-Mohammadi, Magnus Jansson, Arash Owrang +2
We consider the problem of direction-of-arrival (DOA) estimation in unknown partially correlated noise environments where the noise covariance matrix is sparse. A sparse noise cova…
Recovery of Low-Rank Matrices under Affine Constraints via a Smoothed Rank Function
Mohammadreza Malek-Mohammadi, Massoud Babaie-Zadeh, Arash Amini +1
In this paper, the problem of matrix rank minimization under affine constraints is addressed. The state-of-the-art algorithms can recover matrices with a rank much less than what i…
Statistical Performance Analysis of MDL Source Enumeration in Array Processing
Farzan Haddadi, Mohammadreza Malekmohammadi, Mohammad Mahdi Nayebi +1
In this correspondence, we focus on the performance analysis of the widely-used minimum description length (MDL) source enumeration technique in array processing. Unfortunately, av…