学术交流
史晓平博士学术报告会

信息来源:暂无 发布日期: 2017-07-17浏览次数:

报告题目: A consistent and powerful graph based change-point test for high-dimensional data

报告人: 史晓平博士(加拿大汤姆森河大学(Thompson Rivers University),助理教授)

报告时间: 2017年7月17日(周一)  16:30-17:30

报告地点: 安徽大学磬苑校区数学科学学院H306

报告摘要:Modeling high-dimensional time series is necessary in many fields such as network evolution, image analysis and text analysis. For instance, the time of cell divisions can be accessed utilizing an automatic embryo monitoring system by a time-lapse observation. When a cell divides at some time point, the distribution of pixel values in the corresponding frame will change, and hence the detection of cell divisions can be formulated as a multiple change-point problem. The aim is to automatically detect multiple change points: the time points of first, second and third division cycles. The change-point detection is carried out by using a Bayesian-type statistic based on the shortest Hamiltonian path, and the change-point is estimated by Ratio Cut.  A permutation procedure is applied to approximate the significance of Bayesian-type statistics. The change-point test is proved to be consistent, and an error probability in change-point estimation is provided. Compared to the test of Chen and Zhang (2015) based on the minimum spanning tree, the new test is particularly powerful against alternatives with a shift in variance and is accurate in change-point estimation, as shown in simulation studies. Its applicability in tracking cell division is illustrated.

主办单位:数学科学学院

欢迎各位老师、同学届时前往!

       科学技术处

      2017年7月16日

报告人简介:

史晓平,2002年毕业于重庆大学应用数学本科专业,而后加入合肥工业大学担任助教职务。2008年获得中国科学技术大学概率统计硕士学位,随后赴加拿大约克大学攻读统计博士学位并于2011年获得博士学位。紧接着在多伦多大学从事博士后研究,随后分别在约克大学和圣弗朗西斯·格扎维埃大学任教,2016年加入汤姆森河大学,担任助理教授职务。主要从事领域包括分布的鞍点近似、复合似然推断、变量选择、基于图论方法的变点检测以及图像去噪声等。许多成果已在Proceedings of the National Academy of Sciences(美国国家科学院院刊2篇)、Statistica Sinica、Computational Statistics and Data Analysis、Computational Statistics、Journal of Mathematical Analysis and Applications、Science China Mathematics、Canadian Journal of Statistics、Statistics and Probability Letters、Australian and New Zealand Journal of Statistics、Journal of Statistical Theory and Practice等杂志上发表。更多信息可参见其网页:https://kamino.tru.ca/experts/home/main/bio.html?id=xshi