1 code implementation • 11 Apr 2024 • Nastaran Saadati, Minh Pham, Nasla Saleem, Joshua R. Waite, Aditya Balu, Zhanhong Jiang, Chinmay Hegde, Soumik Sarkar
This DIMAT paradigm presents a new opportunity for the future decentralized learning, enhancing its adaptability to real-world with sparse and light-weight communication and computation.
no code implementations • 7 Nov 2022 • Biswajit Khara, Ethan Herron, Zhanhong Jiang, Aditya Balu, Chih-Hsuan Yang, Kumar Saurabh, Anushrut Jignasu, Soumik Sarkar, Chinmay Hegde, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention.
no code implementations • 21 Sep 2022 • Zhanhong Jiang, Aditya Balu, Xian Yeow Lee, Young M. Lee, Chinmay Hegde, Soumik Sarkar
To address these two issues, we propose a novel composite regret with a new network regret-based metric to evaluate distributed online optimization algorithms.
no code implementations • 28 Aug 2022 • Haoxiang Wang, Zhanhong Jiang, Chao Liu, Soumik Sarkar, Dongxiang Jiang, Young M. Lee
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.
1 code implementation • 6 Dec 2021 • Zhanhong Jiang, Xian Yeow Lee, Sin Yong Tan, Kai Liang Tan, Aditya Balu, Young M. Lee, Chinmay Hegde, Soumik Sarkar
We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations.
Multi-agent Reinforcement Learning Policy Gradient Methods +3
1 code implementation • 2 Mar 2021 • Yasaman Esfandiari, Sin Yong Tan, Zhanhong Jiang, Aditya Balu, Ethan Herron, Chinmay Hegde, Soumik Sarkar
Inspired by ideas from continual learning, we propose Cross-Gradient Aggregation (CGA), a novel decentralized learning algorithm where (i) each agent aggregates cross-gradient information, i. e., derivatives of its model with respect to its neighbors' datasets, and (ii) updates its model using a projected gradient based on quadratic programming (QP).
no code implementations • 21 Oct 2020 • Aditya Balu, Zhanhong Jiang, Sin Yong Tan, Chinmay Hedge, Young M Lee, Soumik Sarkar
In this context, we propose and analyze a novel decentralized deep learning algorithm where the agents interact over a fixed communication topology (without a central server).
2 code implementations • 11 Aug 2020 • Tryambak Gangopadhyay, Sin Yong Tan, Zhanhong Jiang, Rui Meng, Soumik Sarkar
Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal correlations can significantly benefit the domain experts.
no code implementations • 8 Nov 2019 • Zhanhong Jiang, Young M. Lee
This study proposes a deep supervised domain adaptation (DSDA) method for thermal dynamics modeling of building indoor temperature evolution and energy consumption.
no code implementations • 15 Oct 2019 • Zhanhong Jiang, Aditya Balu, Sin Yong Tan, Young M. Lee, Chinmay Hegde, Soumik Sarkar
In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments.
no code implementations • NeurIPS 2018 • Aaron J. Havens, Zhanhong Jiang, Soumik Sarkar
The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents.
no code implementations • 31 May 2018 • Chao Liu, Kin Gwn Lore, Zhanhong Jiang, Soumik Sarkar
Performance monitoring, anomaly detection, and root-cause analysis in complex cyber-physical systems (CPSs) are often highly intractable due to widely diverse operational modes, disparate data types, and complex fault propagation mechanisms.
no code implementations • 30 May 2018 • Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar
In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality.
no code implementations • NeurIPS 2017 • Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar
There is significant recent interest to parallelize deep learning algorithms in order to handle the enormous growth in data and model sizes.
no code implementations • 3 Feb 2017 • Zhanhong Jiang, Chao Liu, Adedotun Akintayo, Gregor Henze, Soumik Sarkar
This paper presents a novel data-driven technique based on the spatiotemporal pattern network (STPN) for energy/power prediction for complex dynamical systems.
no code implementations • 24 Dec 2015 • Chao Liu, Sambuddha Ghosal, Zhanhong Jiang, Soumik Sarkar
Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems.