12 citations · 14 across the 11 of their papers we have counts for
13 papers
Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers
Charles Kulick, Armenak Petrosyan, Sui Tang
We propose a decoupled, layerwise method for structurally sparsifying the fully connected layers of pretrained neural networks. Rather than penalizing all layers jointly, our appro…
Reconstructing Graph Signals from Noisy Dynamical Samples
Akram Aldroubi, Victor Bailey, Ilya Krishtal +2
We investigate the dynamical sampling space-time trade-off problem within a graph setting. Specifically, we derive necessary and sufficient conditions for space-time sampling that…
Orthogonally weighted regularization for rank-aware joint sparse recovery: algorithm and analysis
Armenak Petrosyan, Konstantin Pieper, Hoang Tran
We propose and analyze an efficient algorithm for solving the joint sparse recovery problem using a new regularization-based method, named orthogonally weighted ($\mat…
Nonconvex regularization for sparse neural networks
Konstantin Pieper, Armenak Petrosyan
Convex regularization using an infinite dictionary of neurons has been suggested for constructing neural networks with desired approximation guarantees, but can be affecte…
Neural network integral representations with the ReLU activation function
Armenak Petrosyan, Anton Dereventsov, Clayton Webster
In this effort, we derive a formula for the integral representation of a shallow neural network with the ReLU activation function. We assume that the outer weighs admit a finite $L…
A Weighted -Minimization Approach For Wavelet Reconstruction of Signals and Images
Joseph Daws, Armenak Petrosyan, Hoang Tran +1
In this effort, we propose a convex optimization approach based on weighted -regularization for reconstructing objects of interest, such as signals or images, that are spar…
Local-to-global frames and applications to dynamical sampling problem
Akram Aldroubi, Carlos Cabrelli, Ursula Molter +1
In this paper we consider systems of vectors in a Hilbert space of the form where and are countable sets o…
Greedy Shallow Networks: An Approach for Constructing and Training Neural Networks
Anton Dereventsov, Armenak Petrosyan, Clayton Webster
We present a greedy-based approach to construct an efficient single hidden layer neural network with the ReLU activation that approximates a target function. In our approach we obt…
Reconstruction of jointly sparse vectors via manifold optimization
Armenak Petrosyan, Hoang Tran, Clayton Webster
In this paper, we consider the challenge of reconstructing jointly sparse vectors from linear measurements. Firstly, we show that by utilizing the rank of the output data matrix we…
An Operator theoretic approach to the convergence of rearranged Fourier series
Keaton Hamm, Ben Hayes, Armenak Petrosyan
This article studies the rearrangement problem for Fourier series introduced by P.L. Ulyanov, who conjectured that every continuous function on the torus admits a rearrangement of…
Frames Induced by the Action of Continuous Powers of an Operator
Akram Aldroubi, Longxiu Huang, Armenak Petrosyan
We investigate systems of the form where is a normal operator in a separable Hilbert space , $\mathcal{G}\s…
Dynamical sampling and systems from iterative actions of operators
Akram Aldroubi, Armenak Petrosyan
We review some of the recent developments and prove new results concerning frames and Bessel systems generated by iterations of the form , where…
Iterative actions of normal operators
A. Aldroubi, C. Cabrelli, A. F. Çakmak +2
Let be a normal operator in a Hilbert space , and let be a countable set of vectors. We investigate the relations between , $\…