no code implementations • 31 Jan 2024 • Maximilian Arnold, Bence Major, Fabio Valerio Massoli, Joseph B. Soriaga, Arash Behboodi
In the context of communication networks, digital twin technology provides a means to replicate the radio frequency (RF) propagation environment as well as the system behaviour, allowing for a way to optimize the performance of a deployed system based on simulations.
no code implementations • 16 Nov 2023 • Gabriele Cesa, Arash Behboodi
The intermediate features of our networks live in these vector spaces and we leverage the associated sheaf Laplacian to construct more complex linear messages between them.
no code implementations • 14 Nov 2023 • Giovanni Luca Marchetti, Gabriele Cesa, Kumar Pratik, Arash Behboodi
Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice.
no code implementations • 6 Oct 2023 • Thomas M. Hehn, Tribhuvanesh Orekondy, Ori Shental, Arash Behboodi, Juan Bucheli, Akash Doshi, June Namgoong, Taesang Yoo, Ashwin Sampath, Joseph B. Soriaga
The transformer model attends to the regions that are relevant for path loss prediction and, therefore, scales efficiently to maps of different size.
1 code implementation • NeurIPS 2023 • Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort
We provide an extensive comparison between the two techniques for compressing deep neural networks.
no code implementations • 3 Nov 2022 • Hamed Pezeshki, Fabio Valerio Massoli, Arash Behboodi, Taesang Yoo, Arumugam Kannan, Mahmoud Taherzadeh Boroujeni, Qiaoyu Li, Tao Luo, Joseph B. Soriaga
Analog beamforming is the predominant approach for millimeter wave (mmWave) communication given its favorable characteristics for limited-resource devices.
no code implementations • 24 Oct 2022 • Arash Behboodi, Gabriele Cesa, Taco Cohen
Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model.
no code implementations • 15 Sep 2022 • Gouranga Charan, Umut Demirhan, João Morais, Arash Behboodi, Hamed Pezeshki, Ahmed Alkhateeb
In this paper, along with the detailed descriptions of the problem statement and the development dataset, we provide a baseline solution that utilizes the user position data to predict the optimal beam indices.
no code implementations • 22 Jul 2022 • Andrey Kuzmin, Mart van Baalen, Markus Nagel, Arash Behboodi
In this paper, we introduce a novel method of neural network weight compression.
no code implementations • 28 Jun 2022 • Anna Kuzina, Kumar Pratik, Fabio Valerio Massoli, Arash Behboodi
In compressed sensing, the goal is to reconstruct the signal from an underdetermined system of linear measurements.
1 code implementation • 18 May 2022 • João Morais, Arash Behboodi, Hamed Pezeshki, Ahmed Alkhateeb
Millimeter-wave (mmWave) communication systems rely on narrow beams for achieving sufficient receive signal power.
no code implementations • 16 Mar 2022 • Tribhuvanesh Orekondy, Arash Behboodi, Joseph B. Soriaga
We propose generative channel modeling to learn statistical channel models from channel input-output measurements.
no code implementations • 15 Mar 2022 • Shreya Kadambi, Arash Behboodi, Joseph B. Soriaga, Max Welling, Roohollah Amiri, Srinivas Yerramalli, Taesang Yoo
The model is based on an encoder-decoder architecture.
no code implementations • 8 Dec 2021 • Ekkehard Schnoor, Arash Behboodi, Holger Rauhut
Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements.
no code implementations • 29 Sep 2021 • Andrey Kuzmin, Mart van Baalen, Markus Nagel, Arash Behboodi
In this paper, we introduce a novel method of weight compression.
no code implementations • 26 Sep 2021 • Kumar Pratik, Rana Ali Amjad, Arash Behboodi, Joseph B. Soriaga, Max Welling
Through extensive experiments on CDL-B channel model, we show that the HKF can be used for tracking the channel over a wide range of Doppler values, matching Kalman filter performance with genie Doppler information.
no code implementations • 29 Oct 2020 • Arash Behboodi, Holger Rauhut, Ekkehard Schnoor
The neural networks in this class are obtained by unfolding iterations of ISTA and learning some of the weights.
no code implementations • ICLR 2020 • Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling
We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization.
no code implementations • 3 Jun 2019 • Emilio Rafael Balda, Arash Behboodi, Niklas Koep, Rudolf Mathar
To study how robustness generalizes, recent works assume that the inputs have bounded $\ell_2$-norm in order to bound the adversarial risk for $\ell_\infty$ attacks with no explicit dimension dependence.
no code implementations • ICLR 2019 • Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
Studying the evolution of information theoretic quantities during Stochastic Gradient Descent (SGD) learning of Artificial Neural Networks (ANNs) has gained popularity in recent years.
1 code implementation • 25 Apr 2019 • Arya Bangun, Arash Behboodi, Rudolf Mathar
It is first shown that random sensing matrices, which consists of random samples of Wigner D-functions, satisfy the Restricted Isometry Property (RIP) with a proper preconditioning and can be used for sparse recovery on the rotation group.
Information Theory Information Theory
no code implementations • 29 Jan 2019 • Peter Langenberg, Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
In this work, this problem is studied through the lens of compression which is captured by the low-rank structure of weight matrices.
no code implementations • 15 Dec 2018 • Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
The framework can be used to propose novel attacks against learning algorithms for classification and regression tasks under various new constraints with closed form solutions in many instances.
no code implementations • 21 Mar 2018 • Linchen Xiao, Arash Behboodi, Rudolf Mathar
Considered as a data-driven approach, Fingerprinting Localization Solutions (FPSs) enjoy huge popularity due to their good performance and minimal environment information requirement.
1 code implementation • 9 Mar 2018 • Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
Moreover, this framework is capable of explaining various existing adversarial methods and can be used to derive new algorithms as well.
no code implementations • ICLR 2018 • Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
We carry out a tensor analysis on the expressive power inter-connections on convolutional arithmetic circuits (ConvACs) and relate our results to standard convolutional networks.