Ali Abbasi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ali Abbasi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Soheil Kolouri
Department of Computer Science Vanderbilt University
2 shared publications - Hamed Pirsiavash
University of California Davis
1 shared publication - Javad Mohammadi
Civil Architectural and Environmental Engineering The University of Texas at Austin Austin Texas USA
1 shared publication - Meiyi Li
The University of Texas at Austin
1 shared publication - Parsa Nooralinejad
CS Department, University of California, Davis, CA, USA
1 shared publication - Soroush Abbasi Koohpayegani
University of California Davis
1 shared publication
Latest Publications
- Open Access
- 25 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 17102-17113
Teaching Networks to Solve Optimization Problems
Leveraging machine learning to facilitate the optimization process is an emerging field that promises to bypass the fundamental computational bottleneck caused by classic iterative solvers in critical applications requiring near-real-time optimization. Most existing approaches focus on learning data-driven optimizers that lead to fewer iterations in solving an optimization. In this paper, we take a different approach and propose to replace the iterative solvers altogether with a trainable parametric set function, that outputs the optimal arguments/parameters of an optimization problem in a single feed-forward. We denote our method as Learning to Optimize the Optimization Process ( LOOP ). We show the feasibility of learning such parametric (set) functions to solve various classic optimization problems, including linear/nonlinear regression, principal component analysis, transport-based coreset, and quadratic programming in supply management applications. In addition, we propose two alternative approaches for learning such parametric functions, with and without a solver in the LOOP . Finally, through various numerical experiments, we show that the trained solvers could be orders of magnitude faster than the classic iterative solvers while providing near-optimal solutions.
- 25 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 17102-17113
Open AccessTeaching Networks to Solve Optimization Problems
Leveraging machine learning to facilitate the optimization process is an emerging field that promises to bypass the fundamental computational bottleneck caused by classic iterative solvers in critical applications requiring near-real-time optimization. Most existing approaches focus on learning data-driven optimizers that lead to fewer iterations in solving an optimization. In this paper, we take a different approach and propose to replace the iterative solvers altogether with a trainable parametric set function, that outputs the optimal arguments/parameters of an optimization problem in a single feed-forward. We denote our method as Learning to Optimize the Optimization Process ( LOOP ). We show the feasibility of learning such parametric (set) functions to solve various classic optimization problems, including linear/nonlinear regression, principal component analysis, transport-based coreset, and quadratic programming in supply management applications. In addition, we propose two alternative approaches for learning such parametric functions, with and without a solver in the LOOP . Finally, through various numerical experiments, we show that the trained solvers could be orders of magnitude faster than the classic iterative solvers while providing near-optimal solutions.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1812-1816
Multi-Agent Lifelong Implicit Neural Learning
Implicit neural representations (INRs) have emerged as powerful tools for the continuous representation of signals, finding applications in imaging, computer graphics, and signal compression. Additionally, decentralized multi-agent systems are crucial in various applications, frequently leading to enhanced reliability and efficiencies in computation and communication. In this paper, we explore using multi-agent Lifelong Learning (LL) systems for learning INRs. We propose a rigorous problem setup and evaluation plan to investigate the efficacy of such systems compared to single-agent and multi-task learning baselines. Our research, conducted across varied dimensions, demonstrates promising results, thereby contributing a novel perspective to the realm of continual learning.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1812-1816
Multi-Agent Lifelong Implicit Neural Learning
Implicit neural representations (INRs) have emerged as powerful tools for the continuous representation of signals, finding applications in imaging, computer graphics, and signal compression. Additionally, decentralized multi-agent systems are crucial in various applications, frequently leading to enhanced reliability and efficiencies in computation and communication. In this paper, we explore using multi-agent Lifelong Learning (LL) systems for learning INRs. We propose a rigorous problem setup and evaluation plan to investigate the efficacy of such systems compared to single-agent and multi-task learning baselines. Our research, conducted across varied dimensions, demonstrates promising results, thereby contributing a novel perspective to the realm of continual learning.