Search

Your search keyword '"Li, Xiangyuan"' showing total 560 results
Start Over Author "Li, Xiangyuan"
560 results on '"Li, Xiangyuan"'

1. Non-asymptotic Estimates for Markov Transition Matrices with Rigorous Error Bounds

Author

Huang, De and Li, Xiangyuan

Subjects
Mathematics - Statistics Theory, Mathematics - Probability, 60J10, 37A25, 62M05
Abstract

We establish non-asymptotic error bounds for the classical Maximal Likelihood Estimation of the transition matrix of a given Markov chain. Meanwhile, in the reversible case, we propose a new reversibility-preserving online Symmetric Counting Estimation of the transition matrix with non-asymptotic deviation bounds. Our analysis is based on a convergence study of certain Markov chains on the length-2 path spaces induced by the original Markov chain., Comment: 21 pages, 7 figures

Published
2024

2. Bernstein-type Inequalities for Markov Chains and Markov Processes: A Simple and Robust Proof

Author

Huang, De and Li, Xiangyuan

Subjects
Mathematics - Probability, 60J05, 60J25, 37A30
Abstract

We establish a new Bernstein-type deviation inequality for general discrete-time Markov chains via an elementary approach. More robust than existing works in the literature, our result only requires the Markov chain to satisfy an iterated Poincar\'e inequality. Moreover, our method can be readily generalized to continuous-time Markov processes., Comment: 13 pages

Published
2024

3. Understanding Representation Learnability of Nonlinear Self-Supervised Learning

Author

Yang, Ruofeng, Li, Xiangyuan, Jiang, Bo, and Li, Shuai

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, treating the nonlinear neural network as a ``black box". However, the accurate learning results of neural networks are crucial for describing the data distribution features learned by SSL models. Our paper is the first to analyze the learning results of the nonlinear SSL model accurately. We consider a toy data distribution that contains two features: the label-related feature and the hidden feature. Unlike previous linear setting work that depends on closed-form solutions, we use the gradient descent algorithm to train a 1-layer nonlinear SSL model with a certain initialization region and prove that the model converges to a local minimum. Furthermore, different from the complex iterative analysis, we propose a new analysis process which uses the exact version of Inverse Function Theorem to accurately describe the features learned by the local minimum. With this local minimum, we prove that the nonlinear SSL model can capture the label-related feature and hidden feature at the same time. In contrast, the nonlinear supervised learning (SL) model can only learn the label-related feature. We also present the learning processes and results of the nonlinear SSL and SL model via simulation experiments.

Published
2024

20. A teosinte-derived allele of ZmSC improves salt tolerance in maize

Author

Li, Xiaofeng, primary, Ma, Qiangqiang, additional, Wang, Xingyu, additional, Zhong, Yunfeng, additional, Zhang, Yibo, additional, Zhang, Ping, additional, Du, Yiyang, additional, Luo, Hanyu, additional, Chen, Yu, additional, Li, Xiangyuan, additional, Li, Yingzheng, additional, He, Ruyu, additional, Zhou, Yang, additional, Li, Yang, additional, Cheng, Mingjun, additional, He, Jianmei, additional, Rong, Tingzhao, additional, and Tang, Qilin, additional

Published
2024
Full Text
View/download PDF

28. The relationship between night shift work and breast cancer incidence: A systematic review and meta-analysis of observational studies

Author

Hong Jiaze, He Yujing, Fu Rongrong, Si Yuexiu, Xu Binbin, Xu Jiaxuan, Li Xiangyuan, and Mao Feiyan

Subjects
breast cancer, night shift work, hazard, hormone receptor, menopausal status, Medicine
Abstract

The purpose of this study was to investigate the relationship between night shift work and breast cancer (BC) incidence. A search was performed in PubMed, EBSCO, Web of Science, and Cochrane Library databases before June 2021. The exposure factor of this study is night shift work, the primary outcome is the risk of BC. A total of 33 observational studies composed of 4,331,782 participants were included. Night shift work increases the risk of BC in the female population (hazard ratio [HR] = 1.20, 95% confidence interval [Cl] = 1.10–1.31, p < 0.001), especially receptor-positive BC, including estrogen receptor (ER)+ BC (HR = 1.35, p < 0.001), progesterone receptor (PR)+ BC (HR = 1.30, p = 0.003), and human epidermal growth factor receptor 2 (HER2)+ BC (HR = 1.42, p < 0.001), but has no effect on HER2− BC (HR = 1.10, p = 0.515) and ER−/PR− BC (HR = 0.98, p = 0.827). The risk of BC was positively correlated with night shift working duration, frequency, and cumulative times. For women who start night work before menopause, night work will increase the incidence of BC (HR = 1.17, p = 0.020), but for women who start night work after menopause, night work does not affect BC (HR = 1.04, p = 0.293). Night work can increase the incidence of BC in the female population. The effect of long working hours, frequency, and the cumulative number of night shifts on BC is influenced by menopausal status.

Published
2022
Full Text
View/download PDF

41. The Overview of Multi-person Pose Estimation Method

Author

Li, Bingyi, Zou, Jiaqi, Wang, Luyao, Li, Xiangyuan, Li, Yue, Lei, Rongjia, Sun, Songlin, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Liang, Qilian, Series Editor, Martin, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Sun, Songlin, editor, Fu, Meixia, editor, and Xu, Lexi, editor

Published
2019
Full Text
View/download PDF

42. Intelligent Fitness Trainer System Based on Human Pose Estimation

Author

Zou, Jiaqi, Li, Bingyi, Wang, Luyao, Li, Yue, Li, Xiangyuan, Lei, Rongjia, Sun, Songlin, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Liang, Qilian, Series Editor, Martin, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Sun, Songlin, editor, Fu, Meixia, editor, and Xu, Lexi, editor

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results