no code implementations • 6 Nov 2023 • Kinjal Bhar, He Bai, Jemin George, Carl Busart
To demonstrate the efficacy of the proposed algorithm, we present simulations on a toy problem as well as on real world data sets to train ML models to perform classification tasks.
no code implementations • 22 Apr 2023 • Wuxia Chen, Taposh Banerjee, Jemin George, Carl Busart
The proposed algorithm exploits a fundamental reward-detection trade-off present in these problems and uses a quickest change detection algorithm to detect the model change.
no code implementations • 16 Nov 2022 • Kinjal Bhar, He Bai, Jemin George, Carl Busart
We present a practical asynchronous data fusion model for networked agents to perform distributed Bayesian learning without sharing raw data.
no code implementations • 26 Feb 2022 • Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush K. Sharma
Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (MASs) is challenging because: (i) each agent has access to only limited information; (ii) issues on convergence or computational complexity emerge due to the curse of dimensionality.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 10 Jan 2022 • Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush. K. Sharma
In this work, we study MARLs with directed coordination graphs, and propose a distributed RL algorithm where the local policy evaluations are based on local value functions.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 26 Jul 2021 • Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush K. Sharma
Recently introduced distributed zeroth-order optimization (ZOO) algorithms have shown their utility in distributed reinforcement learning (RL).
no code implementations • NeurIPS 2020 • Anjaly Parayil, He Bai, Jemin George, Prudhvi Gurram
Motivated by decentralized approaches to machine learning, we propose a collaborative Bayesian learning algorithm taking the form of decentralized Langevin dynamics in a non-convex setting.
no code implementations • 16 Oct 2020 • Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty
Conditions for decomposability, an algorithm for constructing the transformation matrix, a parallel RL algorithm, and robustness analysis when the design is applied to non-homogeneous MAS are presented.
Hierarchical Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 14 Aug 2020 • Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty
The first component optimizes the performance of each independent cluster by solving the smaller-size LQR design problem in a model-free way using an RL algorithm.
1 code implementation • 14 Jul 2020 • Anjaly Parayil, He Bai, Jemin George, Prudhvi Gurram
Motivated by decentralized approaches to machine learning, we propose a collaborative Bayesian learning algorithm taking the form of decentralized Langevin dynamics in a non-convex setting.
no code implementations • 13 May 2020 • Navjot Singh, Deepesh Data, Jemin George, Suhas Diggavi
In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network.
no code implementations • 31 Oct 2019 • Navjot Singh, Deepesh Data, Jemin George, Suhas Diggavi
In this paper, we propose and analyze SPARQ-SGD, which is an event-triggered and compressed algorithm for decentralized training of large-scale machine learning models.
no code implementations • 8 Sep 2019 • Jemin George, Prudhvi Gurram
We develop a Distributed Event-Triggered Stochastic GRAdient Descent (DETSGRAD) algorithm for solving non-convex optimization problems typically encountered in distributed deep learning.
1 code implementation • 19 Aug 2019 • Jemin George, Tao Yang, He Bai, Prudhvi Gurram
Numerical results also show that the proposed distributed algorithm allows the individual agents to recognize the digits even though the training data corresponding to all the digits is not locally available to each agent.
Optimization and Control Systems and Control Systems and Control