Title: Introduction to Machine Learning and Data Mining

Abstract: The course will start from the basic principles of machine learning and end with the frontiers in statistical learning and data mining. The lectures will cover a collection of methods that have been developed in recent years in statistical machine learning and data mining. Specifically, the topics will include: bias-variance trade-off, cross-validation, k-nearest neighbors, logistic regression, linear discriminant analysis and quadratic discriminant analysis, support vector machines and kernel methods, boosting and random forests.

Instructor: Professor Ji Zhu

Bio: Ji Zhu obtained his B.Sc. in Physics from Peking University in 1996 and his Ph.D. in Statistics from Stanford University in 2003. His research interests include statistical learning, high-dimensional data and statistical network analysis. He is also interested in applications in medicine, computational biology, engineering, physics and business. Professor Zhu received a CAREER award from the NSF in 2008 and was elected a member of ISI in 2010 and a fellow of ASA in 2013.

October 26 (Monday) 2015
9:00 am –10:00 am Registration and Breakfast
10:00 am – 10:15 am Welcome

Some tips on developing leadership skills within your organization

Walt Offen (AbbVie Inc)

10:15 am – 10:30 am Keynote Address

Opportunities and professional development for Statisticians

Wei Shen (Ely Lilly)

10:30 am– 10:45 am Break/Networking
10:45 am – 12:00 pm Parallel Session 1


Personalized medicine


Haoda Fu (Eli Lilly)

Enrichment Design with Patient Population Augmentation

Yijie Zhou ( AbbVie)

GUIDE the search of tailoring biomarkers

Michael Man (Eli Lilly and Company)

Searching for optimal treatment rule – a new look on personalized medicine and subgroup identification

Haoda Fu (Eli Lilly and Company)

Parallel Session 2


Challenges in high-dimensional data


Annie Qu

(University of Illinois at Urbana-Champaign)


Regularized estimation of linear functional for high-dimensional time series.

Xiaohui Chen (University of Illinois at Urbana-Champaign)

Selection by partitioning the solution path

Peng Wang (University of Cincinnati)

An augmented ADMM algorithm with application to high-dimensional statistical estimation problem

Yunzhang Zhu (Ohio State University)

12:00  – 1:30 pm Lunch & Poster Session
1:30 pm – 2:45 pm Parallel Session 3


Causal inference and observational studies


Judith Xu


Indirect Treatment Comparisons

Shawn Yu (Takeda)

Bayesian sensitivity analysis to assess the impact of unmeasured confounding in comparative observational study

Xiang Zhang (Eli Lily and Company )

Causal Inference

Alan Fan (Astellas)

Parallel Session 4


Longitudinal and survival analysis


Peter Song

(U of Michigan)

Conditional modeling of longitudinal data with terminal event

Shengchun Kong (Purdue University)

Joint Frailty Models for Zero-Inflated Recurrent Events in the Presence of a Terminal Event

Lei Liu (Northwestern University)

Mixtures of g-priors for hypothesis testing in ANOVA models with a diverging number of parameters

Min Wang (Technical University of Michigan)

2:45 pm – 3:00 pm Break/Networking
3:00 pm – 4:15 pm Parallel Session 5


Novel Statistical Methods and Considerations to Meet Modern Oncology Challenges


Yijie Zhou (AbbVie)

Utilizing the relation between pCR and overall survival in trial design for neoadjuvant breast cancer therapies.

Ming Zhu (AbbVie)

Multi-regional Non-inferiority trials in Oncology.

Alan Rong (Astellas)

Progression-Free Survival: How often you look matters.

Jingyi Liu (Eli Lily)

Parallel Session 6


Bayesian and bioinformatics


Yuan Ji ( The University of Chicago)

MetaXcan: A Scalable Gene-Level Association Test

Hae Kyung Im  (The University of Chicago)

Zodiac: A comprehensive depiction of genetic interactions in cancer using TCGA data

Yuan Ji ( The University of Chicago)

A Scalable Algorithm for Bayesian Variable Selection(SAB) with Application to miRNA-mRNA Regulation in Cancer

Feng Liang (UIUC)

4:20 pm –4:30 pm Poster Awards and Closing Remarks

Lingsong Zhang, Lanju Zhang