Back to MJ's Publications

Publications about 'Accelerated first-order algorithms'
Theses
  1. S. Samuelson. Performance tradeoffs of accelerated first-order optimization algorithms. PhD thesis, University of Southern California, 2024. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient descent, Gradient-flow dynamics, Heavy-ball method, Nesterov's accelerated method, Nonnormal dynamics, Noise amplification, Optimization, Transient growth. [bibtex-entry]


  2. H. Mohammadi. Robustness of gradient methods for data-driven decision making. PhD thesis, University of Southern California, 2022. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Data-driven control, Gradient descent, Gradient-flow dynamics, Heavy-ball method, Integral quadratic constraints, Linear quadratic regulator, Model-free control, Nesterov's accelerated method, Nonconvex optimization, Nonnormal dynamics, Noise amplification, Optimization, Optimal control, Polyak-Lojasiewicz inequality, Random search method, Reinforcement learning, Sample complexity, Second-order moments, Transient growth. [bibtex-entry]


Journal articles
  1. H. Mohammadi, M. Razaviyayn, and M. R. Jovanovic. Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms. IEEE Trans. Automat. Control, 2024. Note: Doi:10.1109/TAC.2024.3453656. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient descent, Fundamental limitations, Heavy-ball method, Nesterov's accelerated method, Nonnormal dynamics, Noise amplification, Second-order moments. [bibtex-entry]


  2. W. Wu, J. Chen, M. R. Jovanovic, and T. T. Georgiou. Tannenbaum's gain-margin optimization meets Polyak's heavy-ball algorithm. IEEE Trans. Automat. Control, 2024. Note: Submitted; also arXiv:2409.19882. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient descent, Fundamental limitations, Heavy-ball method, Integral quadratic constraints, Nesterov's accelerated method, Nevanlinna-Pick interpolation, Optimization, Optimal control, Robust control. [bibtex-entry]


  3. H. Mohammadi, S. Samuelson, and M. R. Jovanovic. Transient growth of accelerated optimization algorithms. IEEE Trans. Automat. Control, 68(3):1823-1830, March 2023. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convex optimization, Gradient descent, Heavy-ball method, Integral quadratic constraints, Nesterov's accelerated method, Nonnormal dynamics, Transient growth. [bibtex-entry]


  4. I. K. Ozaslan and M. R. Jovanovic. Accelerated forward-backward and Douglas-Rachford splitting dynamics. Automatica, 2023. Note: Submitted; also arXiv:2407.20620. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convex Optimization, Forward-backward envelope, Douglas-Rachford splitting, Global exponential stability, Integral quadratic constraints, Nesterov's accelerated method, Non-smooth optimization, Proximal algorithms. [bibtex-entry]


  5. H. Mohammadi, M. Razaviyayn, and M. R. Jovanovic. Robustness of accelerated first-order algorithms for strongly convex optimization problems. IEEE Trans. Automat. Control, 66(6):2480-2495, June 2021. Keyword(s): Accelerated first-order algorithms, Consensus networks, Control for optimization, Convex optimization, Integral quadratic constraints, Linear matrix inequalities, Noise amplification, Second-order moments, Semidefinite programming. [bibtex-entry]


Conference articles
  1. W. Wu, J. Chen, M. R. Jovanovic, and T. T. Georgiou. Frequency-domain synthesis of implicit algorithms. In Proceedings of the 2025 American Control Conference, Denver, CO, 2025. Note: Submitted. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient descent, Heavy-ball method, Integral quadratic constraints, Nesterov's accelerated method, Optimization, Optimal control. [bibtex-entry]


  2. S. Samuelson and M. R. Jovanovic. Tradeoffs between convergence speed and noise amplification in first-order optimization: the role of averaging. In Proceedings of the 2024 American Control Conference, Toronto, Canada, pages 650-655, 2024. Keyword(s): Accelerated first-order algorithms, Averaging, Control for optimization, Convergence rate, Convex optimization, Gradient flow dynamics, Noise amplification, Nonnormal dynamics, Two-step momentum algorithm. [bibtex-entry]


  3. H. Mohammadi, M. Razaviyayn, and M. R. Jovanovic. Noise amplification of momentum-based optimization algorithms. In Proceedings of the 2023 American Control Conference, San Diego, CA, pages 849-854, 2023. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient descent, Heavy-ball method, Nesterov's accelerated method, Noise amplification, Nonnormal dynamics, Two-step momentum algorithm. [bibtex-entry]


  4. S. Samuelson, H. Mohammadi, and M. R. Jovanovic. Performance of noisy higher-order accelerated gradient flow dynamics for strongly convex quadratic optimization problems. In Proceedings of the 2023 American Control Conference, San Diego, CA, pages 3839-3844, 2023. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient flow dynamics, Noise amplification, Nonnormal dynamics, Two-step momentum algorithm. [bibtex-entry]


  5. S. Samuelson, H. Mohammadi, and M. R. Jovanovic. Performance of noisy three-step accelerated first-order optimization algorithms for strongly convex quadratic problems. In Proceedings of the 62nd IEEE Conference on Decision and Control, Singapore, pages 1300-1305, 2023. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convergence rate, Convex optimization, Gradient flow dynamics, Noise amplification, Nonnormal dynamics, Three-step momentum algorithm. [bibtex-entry]


  6. S. Samuelson, H. Mohammadi, and M. R. Jovanovic. On the transient growth of Nesterov's accelerated method for strongly convex optimization problems. In Proceedings of the 59th IEEE Conference on Decision and Control, Jeju Island, Republic of Korea, pages 5911-5916, 2020. Note: (Invited paper). Keyword(s): Accelerated first-order algorithms, Control for optimization, Convex optimization, Gradient descent, Integral quadratic constraints, Nesterov's accelerated method, Nonnormal dynamics, Transient growth. [bibtex-entry]


  7. S. Samuelson, H. Mohammadi, and M. R. Jovanovic. Transient growth of accelerated first-order methods. In Proceedings of the 2020 American Control Conference, Denver, CO, pages 2858-2863, 2020. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convex optimization, Gradient descent, Transient growth. [bibtex-entry]


  8. H. Mohammadi, M. Razaviyayn, and M. R. Jovanovic. Performance of noisy Nesterov's accelerated method for strongly convex optimization problems. In Proceedings of the 2019 American Control Conference, Philadelphia, PA, pages 3426-3431, 2019. Keyword(s): Accelerated first-order algorithms, Control for optimization, Convex optimization, Integral quadratic constraints, Linear matrix inequalities, Noise amplification, Second-order moments, Semidefinite programming. [bibtex-entry]


  9. H. Mohammadi, M. Razaviyayn, and M. R. Jovanovic. Variance amplification of accelerated first-order algorithms for strongly convex quadratic optimization problems. In Proceedings of the 57th IEEE Conference on Decision and Control, Miami, FL, pages 5753-5758, 2018. Keyword(s): Accelerated optimization algorithms, Control for optimization, Input-output analysis, Large-scale networks, Fundamental limitations, Robustness, Variance amplifications. [bibtex-entry]



Back to MJ's Publications




Disclaimer:

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.




Last modified: Sat Oct 5 22:00:41 2024
Author: mihailo.


This document was translated from BibTEX by bibtex2html