This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors. We first establish a centralised VI sensor fusion scheme as a benchmark and analyse the limitations of its decentralised counterpart, which requires sensors to await consensus at each VI iteration. Therefore, we propose a decentralised gradient-based VI framework that optimises the Locally Maximised Evidence Lower Bound (LM-ELBO) instead of the standard ELBO, which reduces the parameter search space and enables faster convergence, making it particularly beneficial for decentralised tracking. This proposed framework is inherently self-evolving, improving with advancements in decentralised optimisation techniques for convergence guarantees and efficiency. Further, we enhance the convergence speed of proposed decentralised schemes using natural gradients and gradient tracking strategies. Results verify that our decentralised VI schemes are empirically equivalent to centralised fusion in tracking performance. Notably, the decentralised natural gradient VI method is the most communication-efficient, with communication costs comparable to suboptimal decentralised strategies while delivering notably higher tracking accuracy.
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
Institute for Imaging, Data and Communications (IDCOM), University of Edinburgh(爱丁堡大学成像、数据与通信研究所(IDCOM));Department of Engineering, University of Cambridge(剑桥大学工程系);School of Mathematics, University of Edinburgh(爱丁堡大学数学学院)
Warm Starts, Cold States: Exploiting Adiabaticity for Variational Ground-States
Institute of Physics, Ecole Polytechnique F\' e d\' e rale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland;Centre for Quantum Science;Engineering, Ecole Polytechnique F\' e d\' e rale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland;Barcelona Supercomputing Center, Plaça Eusebi G\"uell, 1-3, 08034 Barcelona, Spain;Institute for Theoretical Physics, ETH Zürich, 8093, Zürich, Switzerland
Tracking large chemical reaction networks and rare events by neural networks
Institute of Data Science, University of Hong Kong, Hong Kong(数据科学研究所,香港大学);Department of Systems Science, Faculty of Arts and Sciences, Beijing Normal University, Zhuhai 519087, China(艺术与科学学院系统科学系,北京师范大学);School of Physics, University of Electronic Science and Technology of China, Chengdu 611731, China(电子科学与技术大学物理学院);School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing 102206, China(邮电大学物理科学与技术学院);Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing 100190, China(中国科学院理论物理研究所);School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230027, China(科学技术大学网络科学与技术学院);School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024, China(杭州高等研究院基础物理与数学科学学院);Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China(电子科学与技术大学基础与前沿科学研究所);Non-classical Information Science Basic Discipline Research Center of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, China(四川省非经典信息科学基础学科研究中心,电子科学与技术大学)