no code implementations • 16 Apr 2024 • Saeid Pourmand, Wyatt D. Whiting, Alireza Aghasi, Nicholas F. Marshall
This paper studies the geometry of binary hyperdimensional computing (HDC), a computational scheme in which data are encoded using high-dimensional binary vectors.
no code implementations • 29 Mar 2024 • Alireza Aghasi, Saeed Ghadimi
In this paper, we study and analyze zeroth-order stochastic approximation algorithms for solving bilvel problems, when neither the upper/lower objective values, nor their unbiased gradient estimates are available.
no code implementations • 27 Feb 2024 • Cheng Zhen, Nischal Aryal, Arash Termehchy, Alireza Aghasi, Amandeep Singh Chabada
Real-world data is often incomplete and contains missing values.
no code implementations • 28 Jan 2024 • Mohammadreza Doostmohammadian, Alireza Aghasi
The proposed algorithm is all-time feasible, implying that at any termination time of the algorithm, the resource-demand feasibility holds.
no code implementations • 28 Jan 2024 • Mohammadreza Doostmohammadian, Alireza Aghasi, Mohammad Pirani, Ehsan Nekouei, Houman Zarrabi, Reza Keypour, Apostolos I. Rikos, Karl H. Johansson
This survey paper provides a comprehensive analysis of distributed algorithms for addressing the distributed resource allocation (DRA) problem over multi-agent systems.
no code implementations • 30 Nov 2023 • Mohammadreza Doostmohammadian, Alireza Aghasi
Efficient resource allocation and scheduling algorithms are essential for various distributed applications, ranging from wireless networks and cloud computing platforms to autonomous multi-agent systems and swarm robotic networks.
no code implementations • 14 Nov 2023 • Mohammadreza Doostmohammadian, Wei Jiang, Muwahida Liaquat, Alireza Aghasi, Houman Zarrabi
This work, particularly, is an improvement over existing stochastic-weight undirected networks in case of link removal or packet drops.
no code implementations • 27 Oct 2023 • Mohammadreza Doostmohammadian, Alireza Aghasi, Maria Vrakopoulou, Hamid R. Rabiee, Usman A. Khan, Themistoklis Charalambou
This paper proposes two nonlinear dynamics to solve constrained distributed optimization problem for resource allocation over a multi-agent network.
no code implementations • 13 Apr 2023 • Mohammadreza Doostmohammadian, Alireza Aghasi, Houman Zarrabi
The agents solve a consensus-constraint distributed optimization cooperatively via continuous-time dynamics, while the links are subject to strongly sign-preserving odd nonlinear conditions.
no code implementations • 30 Aug 2022 • Mohammadreza Doostmohammadian, Usman A. Khan, Alireza Aghasi, Themistoklis Charalambous
This paper considers distributed resource allocation and sum-preserving constrained optimization over lossy networks, where the links are unreliable and subject to packet drops.
no code implementations • 30 Aug 2022 • Mohammadreza Doostmohammadian, Alireza Aghasi, Apostolos I. Rikos, Andreas Grammenos, Evangelia Kalyvianaki, Christoforos N. Hadjicostis, Karl H. Johansson, Themistoklis Charalambous
This paper considers a network of collaborating agents for local resource allocation subject to nonlinear model constraints.
no code implementations • 26 May 2022 • Alireza Aghasi, MohammadJavad Feizollahi, Saeed Ghadimi
With the significant increase in using robust optimization techniques to train machine learning models, this paper presents a novel robust regression framework that operates by minimizing the uncertainty associated with missing data.
no code implementations • 28 Mar 2022 • Mohammadreza Doostmohammadian, Maria Vrakopoulou, Alireza Aghasi, Themistoklis Charalambous
Motivated by recent development in networking and parallel data-processing, we consider a distributed and localized finite-sum (or fixed-sum) allocation technique to solve resource-constrained convex optimization problems over multi-agent networks (MANs).
no code implementations • 10 Sep 2021 • Mohammadreza Doostmohammadian, Alireza Aghasi, Maria Vrakopoulou, Themistoklis Charalambous
A general nonlinear $1$st-order consensus-based solution for distributed constrained convex optimization is proposed with network resource allocation applications.
no code implementations • 1 Apr 2021 • Mohammadreza Doostmohammadian, Alireza Aghasi, Themistoklis Charalambous, Usman A. Khan
In this paper, we consider the binary classification problem via distributed Support-Vector-Machines (SVM), where the idea is to train a network of agents, with limited share of data, to cooperatively learn the SVM classifier for the global database.
no code implementations • 1 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.
no code implementations • 15 Dec 2020 • Mohammadreza Doostmohammadian, Alireza Aghasi, Mohammad Pirani, Ehsan Nekouei, Usman A. Khan, Themistoklis Charalambous
The idea is to optimally allocate the resources among the group of agents by minimizing the overall cost function subject to fixed sum of resources.
1 code implementation • 19 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.
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.
1 code implementation • 17 Jun 2018 • Alireza Aghasi, Afshin Abdi, Justin Romberg
We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network.
1 code implementation • NeurIPS 2017 • Alireza Aghasi, Afshin Abdi, Nam Nguyen, Justin Romberg
This program seeks a sparse set of weights at each layer that keeps the layer inputs and outputs consistent with the originally trained model.
no code implementations • 29 Mar 2016 • Alireza Aghasi, Barmak Heshmat, Albert Redo-Sanchez, Justin Romberg, Ramesh Raskar
Heavy sweep distortion induced by alignments and inter-reflections of layers of a sample is a major burden in recovering 2D and 3D information in time resolved spectral imaging.
no code implementations • 23 Feb 2016 • Alireza Aghasi, Justin Romberg
We present a mathematical and algorithmic scheme for learning the principal geometric elements in an image or 3D object.