79 citations · 276 across the 27 of their papers we have counts for
27 papers · 1 filter
L2T-Hyena: Enhancing State-Space Models with an Adaptive Learn-to-Teach Framework
Fatemeh Sohbati, Farzan Haddadi, Hamid Salahinejad
State-space models (SSMs) have recently emerged as efficient alternatives to computationally intensive architectures such as Transformers for sequence modeling. However, their trai…
Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks
Sajad Faramarzi, Farzan Haddadi, Sajjad Amini +2
Conventional matrix completion methods approximate the missing values by assuming the matrix to be low-rank, which leads to a linear approximation of missing values. It has been sh…
Blind Two-Dimensional Super Resolution in Multiple Input Single Output Linear Systems
Shahedeh Sayyari, Sajad Daei, Farzan Haddadi
In this paper, we consider a multiple-input single-output (MISO) linear time-varying system whose output is a superposition of scaled and time-frequency shifted versions of inputs.…
Multi-weight Nuclear Norm Minimization for Low-rank Matrix Recovery in Presence of Subspace Prior Information
Hamideh Sadat Fazael Ardakani, Sajad Daei, Farzan Haddadi
Weighted nuclear norm minimization has been recently recognized as a technique for reconstruction of a low-rank matrix from compressively sampled measurements when some prior infor…
Off-the-grid Recovery of Time and Frequency Shifts with Multiple Measurement Vectors
Maral Safari, Sajad Daei, Farzan Haddadi
We address the problem of estimating time and frequency shifts of a known waveform in the presence of multiple measurement vectors (MMVs). This problem naturally arises in radar im…
Living near the edge: A lower-bound on the phase transition of total variation minimization
Sajad Daei, Farzan Haddadi, Arash Amini
This work is about the total variation (TV) minimization which is used for recovering gradient-sparse signals from compressed measurements. Recent studies indicate that TV minimiza…