学术报告

题      目：High Dimensional Data Completion

报  告  人：吴国宝(Michael K. Ng)  教授  (邀请人：陈小山 )

                                  香港大学

时      间：8月15日  10：00-11：00

地     点：数科院东楼401

报告人简介:

        香港大学数学系讲座教授 (chair professor)，美国工业与应用数学学会会士，冯康科学计算奖得主。1990年毕业于香港大学数学系，1992年获香港大学硕士学位，1995年获香港中文大学博士学位。研究方向包括科学计算、图像与视觉处理、数据挖掘、生物信息、人工智能与机器学习等。先后担任一些知名期刊的主编和副主编，包括SIAM Journal on Imaging Sciences，SIAM Journal on Scientific Computing，Journal of Scientific Computing，Journal of Computational and Applied Mathematics等。发表学术论文700多篇，著作多部，论著引用次数多达2万多次。

摘      要：

       In recent years, high dimensional data completion has been extensively studied and analyzed, which can be applied to many data science applications such as recommendation, image recovery and one-bit data statistical estimation. In this talk, we present several variants of data completion models and their applications using linear algebra techniques. We provide theoretical insight to create a rigorous scientific basis for solving such data completion problems. Numerical examples are also given to demonstrate the usefulness of these models.