LOGIN ENGLISH

제목 [학술세미나] [특별세미나] 12월 19일(수), 12월 20일(목) 16시 특별세미나 안내
작성일 2018-12-14 08:52:45
내용 [특별세미나] 12월 19일(수), 12월 20일(목) 16시 특별세미나 안내

▪제목 : Massive-scale Sparse Inverse Covariance Matrix estimation
          : a data science perspective
▪연사 : Sang-Yun Oh (UC Santa Barbara)
▪일시 : 2018년 12월 19일(수) PM 16:00 - 17:00
▪장소 : 25동 210호
 
초 록
Across a variety of scientific disciplines, sparse inverse covariance estimation is a popular tool for capturing the underlying dependency relationships in multivariate data. HP-CONCORD method is a highly scalable optimization method for estimating a sparse inverse covariance matrix based on a regularized pseudolikelihood framework, named CONCORD, without assuming Gaussianity. Our parallel proximal gradient method uses a novel communication-avoiding linear algebra algorithm and runs across a multi-node cluster with up to 1k nodes (24k cores), achieving parallel scalability on problems with up to ≈819 billion parameters (1.28 million dimensions); even on a single node, HP-CONCORD demonstrates scalability, outperforming a state-of-the-art method. We also use HP-CONCORD to estimate the underlying dependency structure of the brain from fMRI data and use the result to identify functional regions automatically.


▪제목 : Having fun with data science tools and case studies
▪연사 : Sang-Yun Oh (UC Santa Barbara)
▪일시 : 2018년 12월 20일(목) PM 16:00 - 17:00
▪장소 : 25동 210호
 
초 록
Data scientists use many different mathematical and software tools. When analyzing real datasets, a broad knowledge of software and mathematical tools can make many tasks faster and/or simpler. In this talk, I will discuss some useful tools in data science. In addition to an overview, basketball shooting pattern analysis and yelp review topic discovery will illustrate the use of Jupyter and non-negative matrix factorization in practical situations.


 ※주관 : 통계연구소
파일 세미나 안내_181219_오상윤.hwp [14KB]
세미나 안내_181220_오상윤.hwp [12KB]