Collaborative Proposal: International Research and Education: Workshops in Statistics

“统计学国际研究与教育研讨会”将资助24名美国参与者，包括6名博士后和4名研究生，在未来两年在中国参加两个不同的、为期4天的研讨会。第一次关于机器学习和数据挖掘的研讨会将于2007年6月11-14日在北京举行，第二次关于生物信息学的研讨会将于2008年6月9-12日在杭州举行。每一个研讨会都将遵循一个更广泛参加的北京-杭州国际数学暑期学校，该学校在过去三年中由本提案中的伙伴组织召集。此次研讨会的美方合作代表分别是明尼苏达大学双城分校统计学教授沈晓彤博士和哥伦比亚大学统计学教授应志良教授。中国同行组织者分别是北京中国科学院系统科学研究所李谷英教授和杭州浙江大学数学系林正言教授。第一次机器学习和数据挖掘研讨会的主题有可能在大边际分类、增强集成方法、稀疏和半监督学习聚类、文本和数据挖掘方面取得重大进展。第二届生物信息学研讨会也有很强的潜力来解决基因聚类和调控、微阵列在癌症基因组学和信号传导方面的基础研究问题。这两个研讨会都为美国研究人员提供了一个独特的机会来发展合作，并获得使用中国最近汇总的大型数据库的专业知识。与会者包括著名的专家，这将大大有利于美国早期职业统计学家参加研讨会。

ABSTRACT OISE-0634639-SHEN, Xiaotong, University of Minnesota-Twin CitiesOISE-0634596-YING, Zhiliang, Columbia University "International Research and Education Workshops in Statistics"This award supports a total of twenty-four U.S. participants, including six post-docs and four graduate students, to attend two distinct, four-day workshops in China over the next two years. The first workshop on machine learning and data mining, will be held in Beijing June 11-14, 2007, and the second, on bioinformatics, will be held in Hangzhou June 9-12, 2008. Each workshop will follow a more widely attended Beijing-Hangzhou International Mathematics Summer School which has been convened by the partner organizations in this proposal for the past three years. The respective U.S. Co-PIs for the workshops are Dr. Xiaotong Shen, Professor of Statistics at the University of Minnesota-Twin Cities, and Professor Zhiliang Ying, Professor of Statistics at Columbia University. The Chinese counterpart organizers respectively are LI, Guying, Professor, Institute of Systems Science, Chinese Academy of Sciences in Beijing, and LIN, Zhengyan, Professor of Mathematics at Zhejiang University in Hangzhou, China. Topics for the first workshop in machine learning and data mining have the potential to lead to significant advances in large margin classification, boosting ensemble methods, sparse and semi-supervised learning clustering, text and data mining. The second workshop on bioinformatics also has strong potential to address fundamental research issues in gene clustering and regulation, micro array in cancer genomics, and signaling. Both workshops present U.S. researchers with a unique opportunity to develop collaborations and gain access to expertise in using recently aggregated, large databases in China. The attendees include notable experts that will greatly benefit U.S. early-career statisticians participating in the workshops.