Transactions on Machine Learning Research · July 2026
On-the-go Forgetting without Explicit Unlearning via ERASE
Kushal Chakrabarti, Mayank Baranwal
Research output
Publications
Selected and recent work across trustworthy AI, distributed and federated learning, optimization, control, and estimation. Google Scholar remains the canonical source for citation counts and indexing.
2026
AISTATS 2026 · Poster
Securing Model Weights Against Eavesdropping Adversaries in Federated Learning Using Quantization
Kushal Chakrabarti, Dipankar Maity
UAI 2026 · Accepted
Quantized Stochastic Primal–Dual Methods for Distributed Optimization under Relaxed Global Geometry
Susmit Sarkar, Abhinav Raghuvanshi, Kushal Chakrabarti, Mayank Baranwal
IJCNN 2026 · Accepted
Enhancing Robustness of Federated Learning via Server Learning
Van Sy Mai, Richard J. La, Kushal Chakrabarti, Dipankar Maity
IEEE CDC 2026 · Accepted
Distributed Algorithm for Linear Least Squares Problems via Iteratively Preconditioning by Successive Over-Relaxation
Tianchen Liu, Kushal Chakrabarti
International Journal of Robust and Nonlinear Control · 2026
System-Level Protection of Preconditioned PI Consensus Algorithms Against Eavesdropping Adversaries via Innovation-Shared Inter-Agent Communication
Kushal Chakrabarti et al.
2025
IEEE CDC 2025
On Model Protection in Federated Learning against Eavesdropping Attacks
Dipankar Maity, Kushal Chakrabarti
2024
Preprint
Distributed Optimization via Energy Conservation Laws in Dilated Coordinates
Kushal Chakrabarti, Mayank Baranwal
IEEE Control Systems Letters · Vol. 8
Novel Iteratively Preconditioned Gradient-Descent Algorithm via Successive Over-Relaxation Formulation
Tianchen Liu, Kushal Chakrabarti, Nikhil Chopra
ECAI 2024
A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality
Kushal Chakrabarti, Mayank Baranwal
IEEE Control Systems Letters · Vol. 8
On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
Kushal Chakrabarti, Nikhil Chopra
Automatica · Vol. 160
A Control Theoretic Framework for Adaptive Gradient Optimizers
Kushal Chakrabarti, Nikhil Chopra
2023
IEEE CDC 2023
Iteratively Preconditioned Gradient-Descent Approach for Moving Horizon Estimation Problems
Tianchen Liu, Kushal Chakrabarti, Nikhil Chopra
American Control Conference 2023
IPG Observer: A Newton-type Observer Robust to Measurement Noise
Kushal Chakrabarti, Nikhil Chopra
2022
IEEE Transactions on Control of Network Systems · Vol. 9(2)
On Pre-Conditioning of Decentralized Gradient-Descent when Solving a System of Linear Equations
Kushal Chakrabarti, N. Gupta, Nikhil Chopra
Automatica · Vol. 137
Iterative Pre-conditioning for Expediting the Distributed Gradient-Descent Method: The Case of Linear Least-Squares Problem
Kushal Chakrabarti, N. Gupta, Nikhil Chopra
2021
IEEE CDC 2021
Generalized AdaGrad (G-AdaGrad) and Adam: A State-Space Perspective
Kushal Chakrabarti, Nikhil Chopra
2020
American Control Conference 2020
Iterative Pre-conditioning to Expedite the Gradient-Descent Method
Kushal Chakrabarti, N. Gupta, Nikhil Chopra
IEEE Control Systems Letters · Vol. 5(6)
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
Kushal Chakrabarti, N. Gupta, Nikhil Chopra