报告嘉宾1：赵拓 (JHU&Princeton)
主持人：操晓春 (中科院信工所)
报告时间：2015年3月25日晚20:30（北京时间）
报告题目：Pathwise Coordinate Optimization for Nonconvex Sparse Learning Problems http://valser.org/webinar/slide/slides/20150325/tuozhao.pdf

文章信息：A General Theory of Pathwise Coordinate Optimization, Tuo Zhao, Han Liu and Tong Zhang [Arxiv, Software]
报告摘要：The pathwise coordinate optimization is one of the most important computational frameworks for solving high dimensional convex and nonconvex sparse learning problems. The pathwise coordinate optimization differs from the classical block coordinate descent algorithms in two salient features: warm start initialization and active set identification. These two features grant superior empirical performance, but at the same time pose significant challenge to theoretical analysis. To tackle this long lasting problem, we develop a new theory showing that these two features play pivotal roles in guaranteeing the optimal statistical and computational performance of the pathwise coordinate optimization. In particular, our analysis provides new theoretical insights on the existing pathwise coordinate optimization framework and indicates its possible theoretical drawbacks. Based on the obtained insights, we modify the existing pathwise coordinate optimization framework and propose a new algorithm which guarantees to converge linearly to a unique sparse local optimum with good statistical properties (e.g. minimax optimality and oracle properties). This is the first result establishing the computational and statistical properties of the pathwise coordinate optimization framework in high dimensions. Thorough numerical experiments are provided to support our theory.
报告人简介：Tuo Zhao is a four year PhD student in Department of Computer Science at Johns Hopkins University. He received his B.S. and M.S. in Computer Science from Harbin Institute of Technology, China. He received his second M.S. in Applied Math from University of Minnesota. He is also affiliated with Statistics Laboratory at Princeton University. His research focuses on large-scale nonparametric learning and its applications to high throughput genomics and neuroimaging. He has published 14 papers on top journals and conferences, and developed several popular open-source software packages for high dimensional sparse modeling. He was the core member of the JHU team winning the INDI ADHD 200 global competition on fMRI imaging-based diagnosis classification in 2011. He is also active in adaptive clinical trial studies and gene expression network analysis. He co-authored a Nature paper on the exonic de novo mutations in autism spectrum disorders in 2012.