陈天石
教授
香港中文大学博士
哈尔滨工业大学工学硕士
哈尔滨工业大学工学学士
陈天石于2008年12月获香港中文大学自动化与计算机辅助工程博士学位。在2009年4月至2015年12月期间,他在瑞典林雪平大学电气工程系自动控制组工作,先任博士后,后任(自2011年4月开始)助理教授。他现在是香港中文大学(深圳)的教授。
他的研究兴趣主要集中在系统辨识和数据驱动控制的人工智能方法,时空大数据的统计建模,高精度控制和系统辨识的渐近理论,具体而言:
- 系统辨识和数据驱动控制的人工智能方法:深度学习方法、贝叶斯推理方法、核方法和正则化方法
- 时空大数据的统计建模:高斯过程回归、贝叶斯流形正则化、物理信息的深度学习方法
- 高精度控制:机器人控制、过程控制、运动控制
- 系统辨识的渐近理论:大样本理论、高维理论
他发表了100多篇论文,包括IFAC自动化学报(IFAC Automatica)和IEEE自动控制汇刊(IEEE Transactions on Automatic Control)上的35篇论文,其中包含1篇综述论文和18篇regular/full类型的论文。他在瑞典、欧洲和中国参与了若干科研项目,作为项目负责人,他迄今为止获得的研究资助总额为1000万元人民币+360万瑞典克朗。
他担任了若干期刊和会议的编委,包括:
- IFAC 自动化学报(IFAC Automatica)的编委(2017年1月至今),
- IEEE自动控制汇刊(IEEE Transactions on Automatic Control)的编委(2023年10月至2026年12月),
- 系统与控制快报(Systems & Control Letters)的编委(2017年1月至2020年12月),
- IEEE自动控制系统协会会议编委会(IEEE CSS Conference Editorial Board)的编委(2016年7月至2019年8月)。
他获得了多项研究和教学奖项,包括:
- 2015年入选中国海外高层次青年人才计划,
- 2020年香港中文大学(深圳)校长学者奖,
- 2021年世界前2%顶尖科学家,
- 2021年香港中文大学(深圳)校长模范教学奖,
- 2022年广东省一流本科课程,
- 2022年深圳市优秀教师奖。
他是2021年在意大利帕多瓦举行的第19届IFAC系统辨识会议的四位大会报告人之一,是正则化系统辨识第一本专著《正则化系统辨识-从数据中学习动态模型》一书的合著者。
[1] Gianluigi Pillonetto, Tianshi Chen, Alessandro Chiuso, Giuseppe De Nicolao, and Lennart Ljung, “Regularized System Identification – Learning Dynamic Models from Data”, Springer, 2022. (open access: https://link.springer.com/book/10.1007/978-3-030-95860-2)
[2] Biqiang Mu, and Tianshi Chen “On Asymptotic Optimality of Cross-Validation based Hyper-parameter Estimators for Kernel-based Regularized System Identification”, IEEE Transactions on Automatic Control, vol. 69(7), pp. 4352 – 4367, 2024.
[3] Xiaozhu Fang and Tianshi Chen, “On Kernel Design for Regularized Non-Causal System Identification”, Automatica, vol. 159, pp. 111335, 2024.
[4] Biqiang Mu, Lennart Ljung and Tianshi Chen, “When cannot regularization be used to improve the least squares estimate in the regularized system identification”, Automatica, vol. 160, pp. 111442, 2024
[5] Yue Ju, Biqiang Mu, Lennart Ljung, and Tianshi Chen, “Asymptotic Theory for Regularized System Identification Part I: Empirical Bayes Hyper-parameter Estimator”, IEEE Transactions on Automatic Control, vol. 68, pp. 7224 – 7239, 2023.
[6] Xian Yu, Xiaozhu Fang, Biqiang Mu, and Tianshi Chen, “Kernel-based Regularized Iterative Learning Control of Repetitive Linear Time-varying Systems”, Automatica, vol. 154, pp. 111047, 2023.
[7] Junpeng Zhang, Yue Ju, Biqiang Mu, Renxin Zhong, and Tianshi Chen, “An Efficient Implementation for Spatial-Temporal Gaussian Process Regression and Its Applications”, Automatica, vol. 147, pp. 110679, 2022.
[8] Tianshi Chen and Martin S. Andersen, “On Semiseparable Kernels and Efficient Implementation of Regularized System Identification and Function Estimation”, Automatica, vol. 132, pp. 109682, 2021.
[9] Martin Lindfors, and Tianshi Chen. “Regularized System Identification in the Presence of Outliers: a Variational EM Approach”, Automatica, vol. 121, pp. 109152, 2020.
[10] Lennart Ljung, Tianshi Chen, and Biqiang Mu. “A Shift in Paradigm for System Identification”, International Journal of Control, vol. 93(2), pp. 173–180, 2020.
[11] Martin S. Andersen and Tianshi Chen, “Smoothing Splines and Rank Structured Matrices: Revisiting the Spline Kernel”, SIAM Journal on Matrix Analysis and Applications, vol. 41, pp. 389–412, 2020.
[12] Tianshi Chen. “Continuous-time DC kernel — a stable generalized first-order spline kernel,” IEEE Transactions on Automatic Control, vol. 63. no. 12, pp. 4442–4447, 2018.
[13] Biqiang Mu, and Tianshi Chen. “On input design for regularized LTI system identification: Power-constrained inputs,” Automatica, vol. 97, pp. 327–338, 2018.
[14] Tianshi Chen and Gianluigi Pillonetto. “On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses,” Automatica, vol. 95, pp. 529–533, 2018.
[15] Biqiang Mu, Tianshi Chen and Lennart Ljung. “On Asymptotic Properties of Hyperparameter Estimators for Kernel-based Regularization Methods,” Automatica, vol. 94, pp. 381–395, 2018.
[16] Tianshi Chen. “On kernel design for regularized LTI system identification,” Automatica, vol. 90, pp. 109-122, 2018.
[17] John Lataire and Tianshi Chen. “Transfer function and transient estimation by Gaussian process regression in the frequency domain,” Automatica, Vol. 72. pp. 217–229, 2016.
[18] Tianshi Chen, Martin Andersen, Lennart Ljung, Alessandro Chiuso, and Gianluigi Pillonetto, “System identification via sparse multiple kernel-based regularization using sequential convex optimization techniques,” IEEE Transactions on Automatic Control, Vol.59, No. 11, pp. 2933–2945, 2014.
[19] Gianluigi Pillonetto, Francesco Dinuzzo, Tianshi Chen, Giuseppe De Nicolao, and Lennart Ljung, “Kernel Methods in System Identification, Machine Learning and Function Estimation: A Survey,” Automatica, Vol.50, No. 3, pp.657–682, 2014.
[20] Tianshi Chen, and Lennart Ljung, “Implementation of algorithms for tuning parameters in regularized least squares problems in system identification,” Automatica, no.8 pp. 1525–1535, 2013.
[21] Tianshi Chen, Henrik Ohlsson, and Lennart Ljung, “On the estimation of transfer functions, Regularizations and Gaussian processes - revisited,” Automatica, no. 8, pp. 1525–1535, 2012.