流形拓展t-过程回归

doi:10.52396/JUST-2021-0026

中国科学技术大学学报 ›› 2021, Vol. 51 ›› Issue (5): 382-389.DOI: 10.52396/JUST-2021-0026

流形拓展t-过程回归

郭世威, 王占锋^*, 吴耀华

中国科学技术大学管理学院统计与金融系,安徽合肥 230026

收稿日期:2021-01-24 修回日期:2021-04-12 出版日期:2021-05-31 发布日期:2021-12-01
通讯作者: * E-mail:zfw@ustc.edu.cn

A manifold extended t-process regression

Guo Shiwei, Wang Zhanfeng^*, Wu Yaohua

Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei 230026, China

Received:2021-01-24 Revised:2021-04-12 Online:2021-05-31 Published:2021-12-01
Contact: * E-mail: zfw@ustc.edu.cn

摘要/Abstract

摘要： 本文提出了一种流形拓展t-过程回归模型,用来分析带有复杂协变量的函数型数据.该流形拓展t-过程回归模型可将协变量数据变换至特征空间,然后用拓展t-过程回归将特征空间数据转换到观测数据空间,从而对观测数据进行建模.我们建立了一个估计程序来估计模型中的参数.对真实数据和模拟数据进行了分析,结果说明所提流形拓展t-过程回归模型是可行的.

关键词: 高斯过程回归, 拓展t-过程回归, 流形, 稳健性

Abstract: A manifold extended t-process regression (meTPR) model is developed to fit functional data with a complicated input space. A manifold method is used to transform covariate data from input space into a feature space, and then an extended t-process regression is used to map feature from feature space into observation space. An estimation procedure is constructed to estimate parameters in the model. Numerical studies are investigated with both synthetic data and real data, and results show that the proposed meTPR model performs well.

Key words: Gaussian process regression, extended t-process regression, manifold, robustness

中图分类号:

O212.7

郭世威, 王占锋, 吴耀华. 流形拓展t-过程回归[J]. 中国科学技术大学学报, 2021, 51(5): 382-389.

GUO Shiwei, WANG Zhanfeng, WU Yaohua. A manifold extended t-process regression[J]. Journal of University of Science and Technology of China, 2021, 51(5): 382-389.

参考文献

[1] Williams C, Rasmussen C. Gaussian processes for regression. Advances in Neural Information Processing Systems, 1995, 8: 514-520.
[2] Rasmussen C E. Gaussian processes in machine learning. In: Summer School on Machine Learning. Berlin: Springer, 2004: 63-71.
[3] Shi J Q, Choi T.Gaussian Process Regression Analysis for Functional data. Boca Raton, FL: CRC Press, 2011.
[4] Sun B, Yao H, Liu T. Short-term wind speed forecasting based on Gaussian process regression model. Proceedings of the Chinese Society for Electrical Engineering, 2012, 32(29): 104-109.
[5] Liu K Y, Fang Y, Liu B G, et al. Intelligent deformation prediction model of tunnel surrounding rock based on genetic-Gaussian process regression coupling algorithm. Journal of the China Railway Society, 2011, 33: 101-106. (In Chinese)
[6] Smola A J, Bartlett P L. Sparse greedy Gaussian process regression. In: Advances in Neural Information Processing Systems 13. Cambridge, MA: MIT Press, 2001: 619-625.
[7] Seiferth D, Chowdhary G, Mühlegg M, et al. Online Gaussian process regression with non-Gaussian likelihood. In 2017 American Control Conference (ACC). IEEE, 2017: 3134-3140.
[8] Banerjee A, Dunson D B, Tokdar S T. Efficient Gaussian process regression for large datasets. Biometrika, 2013, 100: 75-89.
[9] Wauthier F L, Jordan M I. Heavy-tailed process priors for selective shrinkage. In: Advances in Neural Information Processing Systems 23. Cambridge, MA: MIT Press, 2010: 2406-2414.
[10] Yu S, Tresp V, Yu K, et al. Robust multi-task learning with t-processes. In: Proceedings of the 24th International Conference on Machine learning. New York: Association for Computing Machinery, 2007: 1103-1110.
[11] Shah A, Wilson A, Ghahramani Z. Student-t processes as alternatives to Gaussian processes. In: Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics. Cambridge, MA: PMLR, 2014: 877-885.
[12] Jylänki P, Vanhatalo J, Vehtari A. Robust Gaussian process regression with a student-t likelihood. Journal of Machine Learning Research, 2011, 12: 3227-3257.
[13] Wang Z, Shi J Q, Lee Y. Extended t-process regression models. Journal of Statistical Planning and Inference, 2017, 189: 38-60.
[14] Lin Z, Yao F. Functional regression on manifold with contamination.https://arxiv.org/abs/1704.03005.
[15] Sober B, Aizenbud Y, Levin D.Approximation of functions over manifolds: A moving least-squares approach.https://arxiv.org/abs/1711.00765.
[16] Zhou Zhihua, Zhan Dechuan. A manifold learning-based multi-instance regression algorithm. Chinese Journal of Computers, 2006, 29(11): 1948-1955. (In Chinese)
[17] Gao Y, Liu Y J. Diversity based discriminant muti-manifold learning for dimensionality reduction. Automation and Instrumentation, 2020(4): 30-34. (In Chinese)
[18] Fan J F, Chen D C. Combining manifold learning and nonlinear regression for head pose estimation. Journal of Image and Graphics, 2012, 17(8): 1002-1010. (In Chinese)
[19] Calandra R, Peters J, Rasmussen C E, et al. Manifold Gaussian processes for regression. In: 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 2016: 3338-3345.
[20] Mallasto A, Feragen A. Wrapped Gaussian process regression on Riemannian manifolds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2018: 5580-5588.
[21] Lee Y, Nelder J A. Double hierarchical generalized linear models (with discussion). Journal of the Royal Statistical Society: Series C (Applied Statistics), 2006, 55: 139-185.
[22] Xu P, Lee Y, Shi J Q, et al. Automatic detection of significant areas for functional data with directional error control. Statistics in Medicine, 2019, 38: 376-397.
[23] Seeger M W, Kakade S M, Foster D P. Information consistency of nonparametric Gaussian process methods. IEEE Transactions on Information Theory, 2008, 54: 2376-2382.
[24] Berlinet A, Thomas-Agnan C. Reproducing Kernel Hilbert Spaces in Probability and Statistics. Berlin: Springer Science & Business Media, 2011.
[25] Hampel F R, Ronchetti E M, Rousseeuw P J, et al. Robust Statistics: The Approach Based on Influence Functions. Hobooken, NJ: Wiley, 2011.

流形拓展t-过程回归

A manifold extended t-process regression

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	周俊东，尹松庭. 具有有限总曲率子流形的L2调和p形式[J]. 中国科学技术大学学报, 2020, 50(3): 294-299.
[2]	米蓉. Mm(c)×R中具有平行平均曲率的2-调和子流形[J]. 中国科学技术大学学报, 2020, 50(3): 312-316.
[3]	王琪，周志进，冯林安. 欧氏空间中紧致子流形的拟高斯映照[J]. 中国科学技术大学学报, 2020, 50(3): 360-362.
[4]	石陆魁，袁彬，刘文浩. 基于Spark的ISOMAP算法并行化[J]. 中国科学技术大学学报, 2016, 46(9): 711-718.
[5]	吴玉欣，叶桃红. 不同化学热力学建表参数对火焰面模型精度的影响研究[J]. 中国科学技术大学学报, 2014, 44(11): 960-966.
[6]	张晨，尹华锐，李旭，卫国. 蜂窝网络中基于格拉斯曼流形的子空间干扰对齐研究[J]. 中国科学技术大学学报, 2014, 44(1): 48-60.