Generalized AdaGrad (G-AdaGrad) and Adam: A state-space perspective K Chakrabarti, N Chopra 2021 60th IEEE Conference on Decision and Control (CDC), 1496-1501, 2021 | 13 | 2021 |
Iterative pre-conditioning to expedite the gradient-descent method K Chakrabarti, N Gupta, N Chopra 2020 American Control Conference (ACC), 3977-3982, 2020 | 10 | 2020 |
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem K Chakrabarti, N Gupta, N Chopra 2021 American Control Conference (ACC), 2248-2253, 2021 | 6 | 2021 |
A control theoretic framework for adaptive gradient optimizers in machine learning K Chakrabarti, N Chopra arXiv preprint arXiv:2206.02034, 2022 | 5 | 2022 |
Iterative pre-conditioning for expediting the distributed gradient-descent method: The case of linear least-squares problem K Chakrabarti, N Gupta, N Chopra Automatica 137, 110095, 2022 | 5 | 2022 |
On Accelerating Distributed Convex Optimizations K Chakrabarti, N Gupta, N Chopra arXiv preprint arXiv:2108.08670, 2021 | 5 | 2021 |
Iterative pre-conditioning for expediting the gradient-descent method: The distributed linear least-squares problem K Chakrabarti, N Gupta, N Chopra arXiv preprint arXiv:2008.02856, 2020 | 5 | 2020 |
Accelerating distributed SGD for linear regression using iterative pre-conditioning K Chakrabarti, N Gupta, N Chopra Learning for Dynamics and Control, 447-458, 2021 | 3 | 2021 |
A state-space perspective on the expedited gradient methods: Nadam, RAdam, and rescaled gradient flow K Chakrabarti, N Chopra 2022 Eighth Indian Control Conference (ICC), 31-36, 2022 | 2 | 2022 |
Fast distributed beamforming without receiver feedback K Chakrabarti, AS Bedi, FT Dagefu, JN Twigg, N Chopra 2022 56th Asilomar Conference on Signals, Systems, and Computers, 1408-1412, 2022 | 2 | 2022 |
Iteratively preconditioned gradient-descent approach for moving horizon estimation problems T Liu, K Chakrabarti, N Chopra 2023 62nd IEEE Conference on Decision and Control (CDC), 8457-8462, 2023 | 1 | 2023 |
IPG Observer: A Newton-Type Observer Robust to Measurement Noise K Chakrabarti, N Chopra 2023 American Control Conference (ACC), 3069-3074, 2023 | 1 | 2023 |
Analysis and Synthesis of Adaptive Gradient Algorithms in Machine Learning: The Case of AdaBound and MAdamSSM K Chakrabarti, N Chopra 2022 IEEE 61st Conference on Decision and Control (CDC), 795-800, 2022 | 1 | 2022 |
On Preconditioning of Decentralized Gradient-Descent When Solving a System of Linear Equations K Chakrabarti, N Gupta, N Chopra IEEE Transactions on Control of Network Systems 9 (2), 811-822, 2022 | 1 | 2022 |
Control Theory-Inspired Acceleration of the Gradient-Descent Method: Centralized and Distributed K Chakrabarti University of Maryland, College Park, 2022 | 1 | 2022 |
A Kalman filter approach for biomolecular systems with noise covariance updating A Dey, K Chakrabarti, KK Gola, S Sen 2019 Sixth Indian Control Conference (ICC), 262-267, 2019 | 1 | 2019 |
On Distributed Solution of Ill-Conditioned System of Linear Equations under Communication Delays K Chakrabarti, N Gupta, N Chopra 2019 Sixth Indian Control Conference (ICC), 413-418, 2019 | 1 | 2019 |
A control theoretic framework for adaptive gradient optimizers K Chakrabarti, N Chopra Automatica 160, 111466, 2024 | | 2024 |
Accelerating the Iteratively Preconditioned Gradient-Descent Algorithm using Momentum T Liu, K Chakrabarti, N Chopra 2023 Ninth Indian Control Conference (ICC), 68-73, 2023 | | 2023 |
Linear Convergence of Pre-Conditioned PI Consensus Algorithm under Restricted Strong Convexity K Chakrabarti, M Baranwal arXiv preprint arXiv:2310.00419, 2023 | | 2023 |