Back to MJ's Publications
Publications about 'Gradient flow dynamics'


H. Mohammadi.
Robustness of gradient methods for datadriven decision making.
PhD thesis,
University of Southern California,
2022.
Keyword(s): Accelerated firstorder algorithms,
Control for optimization,
Convergence rate,
Convex optimization,
Datadriven control,
Gradient descent,
Gradientflow dynamics,
Heavyball method,
Integral quadratic constraints,
Linear quadratic regulator,
Modelfree control,
Nesterov's accelerated method,
Nonconvex optimization,
Nonnormal dynamics,
Noise amplification,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity,
Secondorder moments,
Transient growth.
[bibtexentry]

H. Mohammadi,
A. Zare,
M. Soltanolkotabi,
and M. R. Jovanovic.
Convergence and sample complexity of gradient methods for the modelfree linearquadratic regulator problem.
IEEE Trans. Automat. Control,
67(5):24352450,
May 2022.
Keyword(s): Datadriven control,
Gradient descent,
Gradientflow dynamics,
Linear quadratic regulator,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity.
[bibtexentry]

N. K. Dhingra,
S. Z. Khong,
and M. R. Jovanovic.
The proximal augmented Lagrangian method for nonsmooth composite optimization.
IEEE Trans. Automat. Control,
64(7):28612868,
July 2019.
Keyword(s): Augmented Lagrangian,
Control for optimization,
Exponential convergence,
Global exponential stability,
Method of multipliers,
Nonsmooth optimization,
Primaldual gradient flow dynamics,
Proximal algorithms,
Proximal augmented Lagrangian,
Regularization for design,
Sparsitypromoting optimal control,
Structured optimal control,
Structure identification.
[bibtexentry]

S. Samuelson and M. R. Jovanovic.
Tradeoffs between convergence speed and noise amplification in firstorder optimization: the role of averaging.
In Proceedings of the 2024 American Control Conference,
Toronto, Canada,
2024.
Note: To appear.
Keyword(s): Accelerated firstorder algorithms,
Averaging,
Control for optimization,
Convergence rate,
Convex optimization,
Gradient flow dynamics,
Noise amplification,
Nonnormal dynamics,
Twostep momentum algorithm.
[bibtexentry]

I. K. Ozaslan and M. R. Jovanovic.
On the global exponential stability of primaldual dynamics for convex problems with linear equality constraints.
In Proceedings of the 2023 American Control Conference,
San Diago, CA,
pages 210215,
2023.
Keyword(s): Global exponential stability,
Gradient flow dynamics,
Lagrangian,
Lyapunov functions,
Primaldual methods.
[bibtexentry]

I. K. Ozaslan and M. R. Jovanovic.
Tight lower bounds on the convergence rate of primaldual dynamics for equality constrained convex problems.
In Proceedings of the 62nd IEEE Conference on Decision and Control,
Singapore,
pages 73127317,
2023.
Keyword(s): Gradient flow dynamics,
Exponential stability,
Integral quadratic constraints,
Primaldual gradient flow dynamics,
Primaldual methods.
[bibtexentry]

S. Samuelson,
H. Mohammadi,
and M. R. Jovanovic.
Performance of noisy higherorder accelerated gradient flow dynamics for strongly convex quadratic optimization problems.
In Proceedings of the 2023 American Control Conference,
San Diego, CA,
pages 38393844,
2023.
Keyword(s): Accelerated firstorder algorithms,
Control for optimization,
Convergence rate,
Convex optimization,
Gradient flow dynamics,
Noise amplification,
Nonnormal dynamics,
Twostep momentum algorithm.
[bibtexentry]

S. Samuelson,
H. Mohammadi,
and M. R. Jovanovic.
Performance of noisy threestep accelerated firstorder optimization algorithms for strongly convex quadratic problems.
In Proceedings of the 62nd IEEE Conference on Decision and Control,
Singapore,
pages 13001305,
2023.
Keyword(s): Accelerated firstorder algorithms,
Control for optimization,
Convergence rate,
Convex optimization,
Gradient flow dynamics,
Noise amplification,
Nonnormal dynamics,
Threestep momentum algorithm.
[bibtexentry]

H. Mohammadi and M. R. Jovanovic.
On the noise amplification of primaldual gradient flow dynamics based on proximal augmented Lagrangian.
In Proceedings of the 2022 American Control Conference,
Atlanta, GA,
pages 926931,
2022.
Keyword(s): Control for optimization,
Convex Optimization,
Integral quadratic constraints,
Linear matrix inequalities,
Noise amplification,
Nonsmooth optimization,
Proximal algorithms,
Primaldual gradient flow dynamics,
Primaldual methods,
Proximal augmented Lagrangian,
Secondorder moments,
Semidefinite programming.
[bibtexentry]

I. K. Ozaslan,
S. HassanMoghaddam,
and M. R. Jovanovic.
On the asymptotic stability of proximal algorithms for convex optimization problems with multiple nonsmooth regularizers.
In Proceedings of the 2022 American Control Conference,
Atlanta, GA,
pages 132137,
2022.
Keyword(s): Control for optimization,
Convex Optimization,
DouglasRachford splitting,
Global asymptotic stability,
Lyapunovbased analysis,
Nonsmooth optimization,
Proximal algorithms,
Primaldual gradient flow dynamics,
Primaldual methods,
Proximal augmented Lagrangian.
[bibtexentry]

I. K. Ozaslan and M. R. Jovanovic.
Exponential convergence of primaldual dynamics for multiblock problems under local error bound condition.
In Proceedings of the 61th IEEE Conference on Decision and Control,
Cancun, Mexico,
pages 75797584,
2022.
Keyword(s): Gradient flow dynamics,
Lyapunov functions,
Proximal algorithms,
Primaldual gradient flow dynamics,
Primaldual methods,
Proximal augmented Lagrangian,
Operator splitting.
[bibtexentry]

H. Mohammadi,
M. Soltanolkotabi,
and M. R. Jovanovic.
On the lack of gradient domination for linear quadratic Gaussian problems with incomplete state information.
In Proceedings of the 60th IEEE Conference on Decision and Control,
Austin, TX,
pages 11201124,
2021.
Keyword(s): Datadriven control,
Gradient descent,
Gradientflow dynamics,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity.
[bibtexentry]

D. Ding and M. R. Jovanovic.
Global exponential stability of primaldual gradient flow dynamics based on the proximal augmented Lagrangian: A Lyapunovbased approach.
In Proceedings of the 59th IEEE Conference on Decision and Control,
Jeju Island, Republic of Korea,
pages 48364841,
2020.
Keyword(s): Augmented Lagrangian,
Control for optimization,
Convex optimization,
Global exponential stability,
Lyapunovbased approach,
Nonsmooth optimization,
Primaldual gradient flow dynamics,
Primaldual methods,
Proximal augmented Lagrangian.
[bibtexentry]

H. Mohammadi,
M. Soltanolkotabi,
and M. R. Jovanovic.
Learning the modelfree linear quadratic regulator via random search.
In Proceedings of Machine Learning Research, 2nd Annual Conference on Learning for Dynamics and Control,
volume 120,
Berkeley, CA,
pages 19,
2020.
Keyword(s): Datadriven control,
Gradient descent,
Gradientflow dynamics,
Linear quadratic regulator,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity.
[bibtexentry]

H. Mohammadi,
M. Soltanolkotabi,
and M. R. Jovanovic.
Random search for learning the linear quadratic regulator.
In Proceedings of the 2020 American Control Conference,
Denver, CO,
pages 47984803,
2020.
Keyword(s): Datadriven control,
Gradient descent,
Gradientflow dynamics,
Linear quadratic regulator,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity.
[bibtexentry]

D. Ding and M. R. Jovanovic.
Global exponential stability of primaldual gradient flow dynamics based on the proximal augmented Lagrangian.
In Proceedings of the 2019 American Control Conference,
Philadelphia, PA,
pages 34143419,
2019.
Keyword(s): Convex optimization,
Global exponential stability,
Nonsmooth optimization,
Primaldual gradient flow dynamics,
Proximal augmented Lagrangian method.
[bibtexentry]

H. Mohammadi,
A. Zare,
M. Soltanolkotabi,
and M. R. Jovanovic.
Global exponential convergence of gradient methods over the nonconvex landscape of the linear quadratic regulator.
In Proceedings of the 58th IEEE Conference on Decision and Control,
Nice, France,
pages 74747479,
2019.
Keyword(s): Datadriven control,
Global exponential stability,
Gradient descent,
Gradientflow dynamics,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
Reinforcement learning.
[bibtexentry]

D. Ding,
B. Hu,
N. K. Dhingra,
and M. R. Jovanovic.
An exponentially convergent primaldual algorithm for nonsmooth composite minimization.
In Proceedings of the 57th IEEE Conference on Decision and Control,
Miami, FL,
pages 49274932,
2018.
Keyword(s): Control for optimization,
Convex optimization,
Euler discretization,
Exponential convergence,
Global exponential stability,
Integral quadratic constraints,
Proximal augmented Lagrangian,
Nonsmooth optimization,
Primaldual gradient flow dynamics,
Proximal algorithms,
Regularization.
[bibtexentry]

D. Ding and M. R. Jovanovic.
A primaldual Laplacian gradient flow dynamics for distributed resource allocation problems.
In Proceedings of the 2018 American Control Conference,
Milwaukee, WI,
pages 53165320,
2018.
Keyword(s): Primaldual gradient flow dynamics,
Proximal augmented Lagrangian,
Distributed resource allocation,
Economic dispatch.
[bibtexentry]

S. HassanMoghaddam and M. R. Jovanovic.
Distributed proximal augmented Lagrangian method for nonsmooth composite optimization.
In Proceedings of the 2018 American Control Conference,
Milwaukee, WI,
pages 20472052,
2018.
Keyword(s): Consensus,
Distributed Optimization,
Nonsmooth optimization,
Primaldual gradient flow dynamics,
Proximal augmented Lagrangian.
[bibtexentry]

S. HassanMoghaddam and M. R. Jovanovic.
On the exponential convergence rate of proximal gradient flow algorithms.
In Proceedings of the 57th IEEE Conference on Decision and Control,
Miami, FL,
pages 42464251,
2018.
Note: (Invited paper).
Keyword(s): Control for optimization,
Distributed optimization,
Forwardbackward envelope,
Exponential convergence,
Global exponential stability,
Gradient flow dynamics,
Largescale systems,
Nonsmooth optimization,
Primaldual method,
Proximal algorithms,
Proximal augmented Lagrangian.
[bibtexentry]

H. Mohammadi,
M. Razaviyayn,
and M. R. Jovanovic.
On the stability of gradient flow dynamics for a rankone matrix approximation problem.
In Proceedings of the 2018 American Control Conference,
Milwaukee, WI,
pages 45334538,
2018.
Keyword(s): Nonconvex optimization,
Stability of nonlinear systems,
Matrix approximation,
Gradient flow dynamics.
[bibtexentry]

H. Mohammadi,
M. Soltanolkotabi,
and M. R. Jovanovic.
Modelfree linear quadratic regulator.
In K. G. Vamvoudakis,
Y. Wan,
F. Lewis,
and D. Cansever, editors, Handbook of Reinforcement Learning and Control.
Springer International Publishing,
2021.
Note: Doi:10.1007/9783030609900.
Keyword(s): Datadriven control,
Gradient descent,
Gradientflow dynamics,
Linear quadratic regulator,
Modelfree control,
Nonconvex optimization,
Optimization,
Optimal control,
PolyakLojasiewicz inequality,
Random search method,
Reinforcement learning,
Sample complexity.
[bibtexentry]
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: Tue Jan 23 11:32:51 2024
Author: mihailo.
This document was translated from BibT_{E}X by
bibtex2html