1 code implementation • 31 Jan 2024 • Hongpeng Guo, Haotian Gu, Xiaoyang Wang, Bo Chen, Eun Kyung Lee, Tamar Eilam, Deming Chen, Klara Nahrstedt
Federated learning (FL) is a machine learning paradigm that allows multiple clients to collaboratively train a shared model while keeping their data on-premise.
no code implementations • 10 Jan 2024 • Haotian Gu, Xin Guo, Timothy L. Jacobs, Philip Kaminsky, Xinyu Li
Freight transportation marketplace rates are typically challenging to forecast accurately.
no code implementations • 6 Nov 2023 • Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum
Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones.
no code implementations • 25 Jul 2023 • Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum
In particular, 1. a strong correlation between the transfer risk and the overall performance of transfer learning methods is established, underscoring the significance of transfer risk as a viable indicator of "transferability"; 2. transfer risk is shown to provide a computationally efficient way to identify appropriate source tasks in transfer learning, enhancing the efficiency and effectiveness of the transfer learning approach; 3. additionally, the numerical experiments offer valuable new insights for portfolio management across these different settings.
no code implementations • 22 May 2023 • Haoyang Cao, Haotian Gu, Xin Guo
Transfer learning is a popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones.
no code implementations • 27 Jan 2023 • Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum
In this paper we build for the first time, to the best of our knowledge, a mathematical framework for the general procedure of transfer learning.
no code implementations • 28 Sep 2022 • Emily Chan, Ciaran O'Hanlon, Carlota Asegurado Marquez, Marwenie Petalcorin, Jorge Mariscal-Harana, Haotian Gu, Raymond J. Kim, Robert M. Judd, Phil Chowienczyk, Julia A. Schnabel, Reza Razavi, Andrew P. King, Bram Ruijsink, Esther Puyol-Antón
Flow analysis carried out using phase contrast cardiac magnetic resonance imaging (PC-CMR) enables the quantification of important parameters that are used in the assessment of cardiovascular function.
1 code implementation • 21 Mar 2022 • Esther Puyol-Antón, Bram Ruijsink, Baldeep S. Sidhu, Justin Gould, Bradley Porter, Mark K. Elliott, Vishal Mehta, Haotian Gu, Miguel Xochicale, Alberto Gomez, Christopher A. Rinaldi, Martin Cowie, Phil Chowienczyk, Reza Razavi, Andrew P. King
In this work we propose for the first time an AI approach for deriving advanced biomarkers of systolic and diastolic LV function from 2-D echocardiography based on segmentations of the full cardiac cycle.
no code implementations • 5 Aug 2021 • Haotian Gu, Xin Guo, Xiaoli Wei, Renyuan Xu
This paper proposes a framework of localized training and decentralized execution to study MARL with network of states.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 17 May 2021 • Haotian Gu, Xin Guo, Xinyu Li
Adversarial training has gained great popularity as one of the most effective defenses for deep neural network and more generally for gradient-based machine learning models against adversarial perturbations on data points.
no code implementations • 10 Feb 2020 • Haotian Gu, Xin Guo, Xiaoli Wei, Renyuan Xu
Multi-agent reinforcement learning (MARL), despite its popularity and empirical success, suffers from the curse of dimensionality.
1 code implementation • 24 Dec 2018 • Haotian Gu, Jack Xin, Zhiwen Zhang
To facilitate the algorithm design and convergence analysis, we decompose the solution of the viscous G-equation into a mean-free part and a mean part, where their evolution equations can be derived accordingly.
Numerical Analysis 65M12, 70H20, 76F25, 78M34, 80A25