主题： Seeking Interpretable Models for High-Dimensional Data
      报告人：郁彬教授（美国加州大学伯克利分校统计系主任）
      时间：2009-9-24，15：00
      地点：数学科学1560会议室

摘要：Information technology has enabled collection of massive amounts of data in science, engineering, social science, finance and beyond. Statistics is the science of data. Extracting useful information from these high-dimensional data is the focus of today's statistical research and practice. After broad success of statistical machine learning on prediction through regularization, interpretability is gaining attention and sparsity has been used as its proxy. With the virtues of both regularization and sparsity, L1 penalized empirical minimization (e.g. Lasso) has been very popular recently.

In this talk, I would like to cover both theory and practice of L1 penalized minimization. First, I will give a brief overview of recent theoretical results on model selection consistency (when p>>n) of Lasso and graphical Lasso. Second, I will present on-going collaborative research with the Gallant Lab at Berkeley on understanding visual pathway. In particular, sparse models (linear, non-linear, and graphical) have been built to relate natural images to fMRI responses in human primary visual cortex area V1. Issues of model validation will be discussed.

李嘉诚基金杰出女性科学家系列讲座：

主题：Personal story: Being a Good Human Being and Loving Challenge（The Li Ka Shing Women in Science Distinguished Speaker Series）

报告人：郁彬教授（美国加州大学伯克利分校统计系主任）
      时间：2009-9-25，16：00
      地点：北京大学生命科学一楼邓佑才报告厅

摘要：In this presentation, I would like to reflect on my path to become a Professor in the departments of Statistics, and Electrical Engineering and Computer Science at University of California, Berkeley. I did not grow up dreaming to become a scientist, as my childhood was spent during cultural revolution. My world then consisted of first-hand observations of grown-up's actions around me, and second hand life experiences through stories of grand parents and aunts and uncles (especially those of strong women in the family). These observations and stories taught me two lessons: one has to be a good human being with empathy towards others; and a woman has to be strong and economically independent.

My connection to science started with a math book given by a cousin when I was a third grader. It was still during the cultural revolution, but doing math problems in the book gave me a much needed refuge and great satisfaction of independence. Attraction to quantitative thinking and kind mentoring of a middle school math teacher eventually led me to the math dept at Peking University in 1980. In the 30 years that followed, I made many choices including a crucial one to become a statistician when I went to the US for Ph.D. In my current position, I enjoy teaching and using statistical thinking and tools to tackle problems from neuroscience, remote-sensing, text-mining, sensor- networks, and finance. I believe my love for challenge, curiosity, open-mindedness, and determination have been driving forces behind my exciting scientific career.