Kushal Chakrabarti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kushal Chakrabarti has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Nikhil Chopra
Department of Mechanical Engineering, University of Maryland, College Park, MD 20742, USA
7 shared publications - Nirupam Gupta
EPFL
3 shared publications Dipankar Maity
Department of Electrical and Computer Engineering University of North Carolina at Charlotte North Carolina USA
1 shared publication- Dipankar Maity
Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, Charlotte, NC, USA
1 shared publication - Mayank Baranwal
Tata Consultancy Services Research, Mumbai, India
1 shared publication - Nirupam Gupta1 shared publication
Latest Publications
- 9 March 2026
- Published by Wiley in International Journal of Robust and Nonlinear Control
System‐Level Protection of Preconditioned PI Consensus Algorithms Against Eavesdropping Adversaries via Innovation‐Shared Inter‐Agent Communication
Preconditioned proportional‐integral consensus ( PrecPIC ) is an efficient algorithm for solving distributed optimization problems. This work investigates its robustness against eavesdropping adversaries, whose interception capabilities are modeled by a Bernoulli process with a positive success probability and whose objective is to infer the final consensus point of distributed agents implementing the algorithm. We demonstrate that the conventional PrecPIC lacks resilience, and in fact remains vulnerable even under minimal adversarial interception probability. To address this, we propose a modified inter‐agent communication protocol that enhances protection without compromising solution accuracy or convergence rate. We analyze how the degree of protection relates to algorithm parameters, the optimization objective, and adversarial capabilities, providing a basis for principled parameter tuning. The inherent trade‐off between protection and convergence speed is also characterized. Numerical experiments validate our theoretical results and demonstrate the improved performance of the proposed modifications relative to similar enhancements applied to alternative algorithms.
- 9 March 2026
- Published by Wiley in International Journal of Robust and Nonlinear Control
System‐Level Protection of Preconditioned PI Consensus Algorithms Against Eavesdropping Adversaries via Innovation‐Shared Inter‐Agent Communication
Preconditioned proportional‐integral consensus ( PrecPIC ) is an efficient algorithm for solving distributed optimization problems. This work investigates its robustness against eavesdropping adversaries, whose interception capabilities are modeled by a Bernoulli process with a positive success probability and whose objective is to infer the final consensus point of distributed agents implementing the algorithm. We demonstrate that the conventional PrecPIC lacks resilience, and in fact remains vulnerable even under minimal adversarial interception probability. To address this, we propose a modified inter‐agent communication protocol that enhances protection without compromising solution accuracy or convergence rate. We analyze how the degree of protection relates to algorithm parameters, the optimization objective, and adversarial capabilities, providing a basis for principled parameter tuning. The inherent trade‐off between protection and convergence speed is also characterized. Numerical experiments validate our theoretical results and demonstrate the improved performance of the proposed modifications relative to similar enhancements applied to alternative algorithms.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 3105-3110
Novel Iteratively Preconditioned Gradient-Descent Algorithm via Successive Over-Relaxation Formulation
We devise a novel quasi-Newton algorithm for solving unconstrained convex optimization problems. The proposed algorithm is built on our previous framework of the iteratively preconditioned gradient-descent (IPG) algorithm. IPG utilized Richardson iteration to update a preconditioner matrix that approximates the inverse of the Hessian matrix. In this work, we substitute the Richardson iteration with a successive over-relaxation (SOR) formulation. The convergence guarantee of the proposed algorithm and its theoretical improvement over vanilla IPG are presented. The algorithm is used in a mobile robot position estimation problem for numerical validation using a moving horizon estimation (MHE) formulation. Compared with IPG, the results demonstrate an improved performance of the proposed algorithm in terms of computational time and the number of iterations needed for convergence, matching our theoretical results.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 3105-3110
Novel Iteratively Preconditioned Gradient-Descent Algorithm via Successive Over-Relaxation Formulation
We devise a novel quasi-Newton algorithm for solving unconstrained convex optimization problems. The proposed algorithm is built on our previous framework of the iteratively preconditioned gradient-descent (IPG) algorithm. IPG utilized Richardson iteration to update a preconditioner matrix that approximates the inverse of the Hessian matrix. In this work, we substitute the Richardson iteration with a successive over-relaxation (SOR) formulation. The convergence guarantee of the proposed algorithm and its theoretical improvement over vanilla IPG are presented. The algorithm is used in a mobile robot position estimation problem for numerical validation using a moving horizon estimation (MHE) formulation. Compared with IPG, the results demonstrate an improved performance of the proposed algorithm in terms of computational time and the number of iterations needed for convergence, matching our theoretical results.
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 2402-2409
A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality
Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well understood as vanilla gradient-descent. A reason is that the dynamic update of the learning rate that helps in faster convergence of these methods also makes their analysis intricate. Particularly, the simple gradient-descent method converges at a linear rate for a class of optimization problems, whereas the practically faster adaptive gradient methods lack such a theoretical guarantee. The Polyak-Łojasiewicz (PL) inequality is the weakest known class, for which linear convergence of gradient-descent and its momentum variants has been proved. Therefore, in this paper, we prove that AdaGrad and Adam, two well-known adaptive gradient methods, converge linearly when the cost function is smooth and satisfies the PL inequality. Our theoretical framework follows a simple and unified approach, applicable to both batch and stochastic gradients, which can potentially be utilized in analyzing linear convergence of other variants of Adam.
- 16 October 2024
- Published by IOS Press
- p. 2402-2409
Open AccessA Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality
Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well understood as vanilla gradient-descent. A reason is that the dynamic update of the learning rate that helps in faster convergence of these methods also makes their analysis intricate. Particularly, the simple gradient-descent method converges at a linear rate for a class of optimization problems, whereas the practically faster adaptive gradient methods lack such a theoretical guarantee. The Polyak-Łojasiewicz (PL) inequality is the weakest known class, for which linear convergence of gradient-descent and its momentum variants has been proved. Therefore, in this paper, we prove that AdaGrad and Adam, two well-known adaptive gradient methods, converge linearly when the cost function is smooth and satisfies the PL inequality. Our theoretical framework follows a simple and unified approach, applicable to both batch and stochastic gradients, which can potentially be utilized in analyzing linear convergence of other variants of Adam.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1715-1720
On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
This letter considers the observer design problem for discrete-time nonlinear dynamical systems with sampled measurements. The recently proposed Iteratively Preconditioned Gradient-Descent (IPG) observer, a Newton-type observer, has been empirically shown to have improved robustness against measurement noise than the prominent nonlinear observers, a property that other Newton-type observers lack. However, no theoretical guarantees on the convergence of the IPG observer were provided. This letter presents a rigorous convergence analysis of the IPG observer for a class of nonlinear systems in deterministic settings, proving its local linear convergence to the actual trajectory. The assumptions are standard in the existing literature of Newton-type observers, and the analysis further confirms the relation of IPG observer with Newton observer, which was only hypothesized earlier.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1715-1720
On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
This letter considers the observer design problem for discrete-time nonlinear dynamical systems with sampled measurements. The recently proposed Iteratively Preconditioned Gradient-Descent (IPG) observer, a Newton-type observer, has been empirically shown to have improved robustness against measurement noise than the prominent nonlinear observers, a property that other Newton-type observers lack. However, no theoretical guarantees on the convergence of the IPG observer were provided. This letter presents a rigorous convergence analysis of the IPG observer for a class of nonlinear systems in deterministic settings, proving its local linear convergence to the actual trajectory. The assumptions are standard in the existing literature of Newton-type observers, and the analysis further confirms the relation of IPG observer with Newton observer, which was only hypothesized earlier.
- 5 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 9 (2) , 811-822
On Preconditioning of Decentralized Gradient-Descent When Solving a System of Linear Equations
This paper considers solving an overdetermined system of linear equations in peer-to-peer multi-agent networks. The network is assumed to be synchronous and (strongly) connected. Each agent has a set of local data points, and their goal is to compute a linear model that fits the collective data points. In principle, the agents can apply the decentralized gradient-descent method (DGD). However, when the data matrix is ill-conditioned, DGD requires many iterations to converge and is unstable against system noise. We propose a decentralized pre-conditioning technique to mitigate the deleterious effects of the data points' conditioning on the convergence rate of DGD. The proposed algorithm converges linearly, with an improved convergence rate than DGD. Considering the practical scenario where the computations performed by the agents are corrupted, we study the robustness guarantee of the proposed algorithm. Additionally, we apply the proposed algorithm for solving decentralized state estimation problems. The empirical results show our proposed state predictor's favorable convergence rate and robustness against system noise compared to prominent decentralized algorithms.
- 5 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 9 (2) , 811-822
On Preconditioning of Decentralized Gradient-Descent When Solving a System of Linear Equations
This paper considers solving an overdetermined system of linear equations in peer-to-peer multi-agent networks. The network is assumed to be synchronous and (strongly) connected. Each agent has a set of local data points, and their goal is to compute a linear model that fits the collective data points. In principle, the agents can apply the decentralized gradient-descent method (DGD). However, when the data matrix is ill-conditioned, DGD requires many iterations to converge and is unstable against system noise. We propose a decentralized pre-conditioning technique to mitigate the deleterious effects of the data points' conditioning on the convergence rate of DGD. The proposed algorithm converges linearly, with an improved convergence rate than DGD. Considering the practical scenario where the computations performed by the agents are corrupted, we study the robustness guarantee of the proposed algorithm. Additionally, we apply the proposed algorithm for solving decentralized state estimation problems. The empirical results show our proposed state predictor's favorable convergence rate and robustness against system noise compared to prominent decentralized algorithms.
- Open Access
Iterative Pre-Conditioning for Expediting the Gradient-Descent Method: The Distributed Linear Least-Squares Problem
This paper considers the multi-agent linear least-squares problem in a server-agent network. In this problem, the system comprises multiple agents, each having a set of local data points, that are connected to a server. The goal for the agents is to compute a linear mathematical model that optimally fits the collective data points held by all the agents, without sharing their individual local data points. This goal can be achieved, in principle, using the server-agent variant of the traditional iterative gradient-descent method. The gradient-descent method converges linearly to a solution, and its rate of convergence is lower bounded by the conditioning of the agents' collective data points. If the data points are ill-conditioned, the gradient-descent method may require a large number of iterations to converge. We propose an iterative pre-conditioning technique that mitigates the deleterious effect of the conditioning of data points on the rate of convergence of the gradient-descent method. We rigorously show that the resulting pre-conditioned gradient-descent method, with the proposed iterative pre-conditioning, achieves superlinear convergence when the least-squares problem has a unique solution. In general, the convergence is linear with improved rate of convergence in comparison to the traditional gradient-descent method and the state-of-the-art accelerated gradient-descent methods. We further illustrate the improved rate of convergence of our proposed algorithm through experiments on different real-world least-squares problems in both noise-free and noisy computation environment.
Open AccessIterative Pre-Conditioning for Expediting the Gradient-Descent Method: The Distributed Linear Least-Squares Problem
This paper considers the multi-agent linear least-squares problem in a server-agent network. In this problem, the system comprises multiple agents, each having a set of local data points, that are connected to a server. The goal for the agents is to compute a linear mathematical model that optimally fits the collective data points held by all the agents, without sharing their individual local data points. This goal can be achieved, in principle, using the server-agent variant of the traditional iterative gradient-descent method. The gradient-descent method converges linearly to a solution, and its rate of convergence is lower bounded by the conditioning of the agents' collective data points. If the data points are ill-conditioned, the gradient-descent method may require a large number of iterations to converge. We propose an iterative pre-conditioning technique that mitigates the deleterious effect of the conditioning of data points on the rate of convergence of the gradient-descent method. We rigorously show that the resulting pre-conditioned gradient-descent method, with the proposed iterative pre-conditioning, achieves superlinear convergence when the least-squares problem has a unique solution. In general, the convergence is linear with improved rate of convergence in comparison to the traditional gradient-descent method and the state-of-the-art accelerated gradient-descent methods. We further illustrate the improved rate of convergence of our proposed algorithm through experiments on different real-world least-squares problems in both noise-free and noisy computation environment.
- Open Access
- 25 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2248-2253
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
This paper considers the problem of multi-agent distributed linear regression in the presence of system noises. In this problem, the system comprises multiple agents wherein each agent locally observes a set of data points, and the agents' goal is to compute a linear model that best fits the collective data points observed by all the agents. We consider a server-based distributed architecture where the agents interact with a common server to solve the problem; however, the server cannot access the agents' data points. We consider a practical scenario wherein the system either has observation noise, i.e., the data points observed by the agents are corrupted, or has process noise, i.e., the computations performed by the server and the agents are corrupted. In noise-free systems, the recently proposed distributed linear regression algorithm, named the Iteratively Pre-conditioned Gradient-descent (IPG) method, has been claimed to converge faster than related methods. In this paper, we study the robustness of the IPG method, against both the observation noise and the process noise. We empirically show that the robustness of the IPG method compares favorably to the state-of-the-art algorithms.
- 25 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2248-2253
Open AccessRobustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
This paper considers the problem of multi-agent distributed linear regression in the presence of system noises. In this problem, the system comprises multiple agents wherein each agent locally observes a set of data points, and the agents' goal is to compute a linear model that best fits the collective data points observed by all the agents. We consider a server-based distributed architecture where the agents interact with a common server to solve the problem; however, the server cannot access the agents' data points. We consider a practical scenario wherein the system either has observation noise, i.e., the data points observed by the agents are corrupted, or has process noise, i.e., the computations performed by the server and the agents are corrupted. In noise-free systems, the recently proposed distributed linear regression algorithm, named the Iteratively Pre-conditioned Gradient-descent (IPG) method, has been claimed to converge faster than related methods. In this paper, we study the robustness of the IPG method, against both the observation noise and the process noise. We empirically show that the robustness of the IPG method compares favorably to the state-of-the-art algorithms.
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 5 (6) , 2180-2185
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
This paper considers the problem of multi-agent distributed linear regression in the presence of system noises. In this problem, the system comprises multiple agents wherein each agent locally observes a set of data points, and the agents’ goal is to compute a linear model that best fits the collective data points observed by all the agents. We consider a server-based distributed architecture where the agents interact with a common server to solve the problem; however, the server cannot access the agents’ data points. We consider a practical scenario wherein the system either has observation noise, i.e., the data points observed by the agents are corrupted, or has process noise, i.e., the computations performed by the server and the agents are corrupted. In noise-free systems, the recently proposed distributed linear regression algorithm, named the Iteratively Pre-conditioned Gradient-descent (IPG) method, has been claimed to converge faster than related methods. In this paper, we study the robustness of the IPG method, against both the observation noise and the process noise. We empirically show that the robustness of the IPG method compares favorably to the state-of-the-art algorithms.
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 5 (6) , 2180-2185
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
This paper considers the problem of multi-agent distributed linear regression in the presence of system noises. In this problem, the system comprises multiple agents wherein each agent locally observes a set of data points, and the agents’ goal is to compute a linear model that best fits the collective data points observed by all the agents. We consider a server-based distributed architecture where the agents interact with a common server to solve the problem; however, the server cannot access the agents’ data points. We consider a practical scenario wherein the system either has observation noise, i.e., the data points observed by the agents are corrupted, or has process noise, i.e., the computations performed by the server and the agents are corrupted. In noise-free systems, the recently proposed distributed linear regression algorithm, named the Iteratively Pre-conditioned Gradient-descent (IPG) method, has been claimed to converge faster than related methods. In this paper, we study the robustness of the IPG method, against both the observation noise and the process noise. We empirically show that the robustness of the IPG method compares favorably to the state-of-the-art algorithms.
- Open Access
Iterative Pre-Conditioning to Expedite the Gradient-Descent Method
This paper considers the problem of multi-agent distributed optimization. In this problem, there are multiple agents in the system, and each agent only knows its local cost function. The objective for the agents is to collectively compute a common minimum of the aggregate of all their local cost functions. In principle, this problem is solvable using a distributed variant of the traditional gradient-descent method, which is an iterative method. However, the speed of convergence of the traditional gradient-descent method is highly influenced by the conditioning of the optimization problem being solved. Specifically, the method requires a large number of iterations to converge to a solution if the optimization problem is ill-conditioned. In this paper, we propose an iterative pre-conditioning approach that can significantly attenuate the influence of the problem's conditioning on the convergence-speed of the gradient-descent method. The proposed pre-conditioning approach can be easily implemented in distributed systems and has minimal computation and communication overhead. For now, we only consider a specific distributed optimization problem wherein the individual local cost functions of the agents are quadratic. Besides the theoretical guarantees, the improved convergence speed of our approach is demonstrated through experiments on a real data-set.
Open AccessIterative Pre-Conditioning to Expedite the Gradient-Descent Method
This paper considers the problem of multi-agent distributed optimization. In this problem, there are multiple agents in the system, and each agent only knows its local cost function. The objective for the agents is to collectively compute a common minimum of the aggregate of all their local cost functions. In principle, this problem is solvable using a distributed variant of the traditional gradient-descent method, which is an iterative method. However, the speed of convergence of the traditional gradient-descent method is highly influenced by the conditioning of the optimization problem being solved. Specifically, the method requires a large number of iterations to converge to a solution if the optimization problem is ill-conditioned. In this paper, we propose an iterative pre-conditioning approach that can significantly attenuate the influence of the problem's conditioning on the convergence-speed of the gradient-descent method. The proposed pre-conditioning approach can be easily implemented in distributed systems and has minimal computation and communication overhead. For now, we only consider a specific distributed optimization problem wherein the individual local cost functions of the agents are quadratic. Besides the theoretical guarantees, the improved convergence speed of our approach is demonstrated through experiments on a real data-set.