Conference on Statistical Learning and Data Science
Department of Statistics & Operations Research
Department of Biostatistics
University of North Carolina at Chapel Hill, NC
June 6 - 8, 2016
UNC logo
Invited Speakers
Key Dates
Conference Venue
Conference Committees
Click here for the printable schedule.
Click here for the abstract book.

June 6 (Monday)


Registration & Continental Breakfast



Professor Amarjit Budhiraja

Chair, Department of Statistics and Operations Research, UNC


Parallel Sessions

Theoretical Statistical Learning

(organized by Yin Xia, UNC; chaired by Jan Hannig, UNC)

Florentina Bunea (Cornell Univ.)

Minimax Optimal Variable Clustering in G-Models

Andrew Nobel (UNC)

Large Average Submatrices of a Gaussian Random Matrix: Behavior of Global and Local optima

Kai Zhang (UNC)

Packing Inference of Correlation for an Arbitrarily Large Number of Variables

Distributed Optimization Methods for Machine Learning

(organized and chaired by Yan Xu, SAS)

Alireza Yektamaram (Lehigh Univ. and SAS)

A Nonconvex Hessian-free Method for Deep Learning Problems

Jorge Silva (SAS)

Learning Good Ensembles: New Approaches

Patrick Koch (SAS)

Local Search Optimization for Hyper-Parameter Tuning

Applied Learning and Analysis

(organized and chaired by Cynthia Rudin, MIT)

John Guerard (McKinley Capital Mgt., LLC )

Robust Regression and Data Mining of Financial Data

Edward McFowland III (Univ. of Minnesota)

Efficient Identification of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Detection

Stefano Traca (MIT)

Regulating Greed Over Time

Network Inference

(organized by Karl Rohe, Univ. Wisconsin Madison; chaired by Bailey Fosdick, Colorado State)

Can Le (Univ. of Michigan)

Structure of sparse random networks

Daniel Sussman (Harvard)

Unbiased Estimation of Causal Effects under Network Interference

Alexander Volfovsky (Harvard/ Duke)

Testing and estimation for relational data




Plenary Talk

Bin Yu, UC Berkeley (chaired by Richard Smith, SAMSI & UNC)

Unveiling the mysteries in spatial gene expression




Parallel Sessions

New Regularization Techniques

(organized by Ji Zhu, Univ. Michigan; chaired by Annie Qu, UIUC)

Yunzhang Zhu (Ohio State Univ.)

High-dimensional Multivariate Regression

Fang Han (Univ. of Washington)

Optimal Structure-Induced Network Estimation

Qing Mai (Florida State)

Multiclass Sparse Discriminant Analysis

Machine Learning on Big Data

(organized and chaired by Matt Taddy, Univ. of Chicago)

Daniel Roy (Univ. of Toronto)

Sparse Random Graphs arising from Exchangeable Random Measures

Rebecca Steorts (Duke)

Why infinite exchangeable mixture models fail for sparse data sets yet microclustering succeeds

Yichao Wu (NCSU)

Principal Weighted Support Vector Machines for Sufficient Dimension Reduction in Binary Classification

High Dimensional Learning Methods and Theory

(organized by Xiaotong Shen, Univ. of Minnesota; chaired by Wei Sun, Fred Hutchinson Cancer Research Center)

Jan Hannig (UNC)

Generalized fiducial inference for high-dimensional data

Yiyuan She (Florida State)

Indirect Gaussian Graph Learning beyond Gaussianity

Zhigen Zhao (Temple Univ.)

A new approach to multiple testing of grouped hypotheses

New Mining Tools for Complex Data

(organized by Hao Helen Zhang, U. Arizona; chaired by Xiaoli Gao, UNC-Greensboro)

Ping Ma (Univ. of Georgia)

Smoothing spline ANOVA for super-large samples

Junming Yin (Univ. of Arizona)

Latent Space Inference of Internet-Scale Networks

Boxiang Wang (Univ. of Minnesota)

Another Look at DWD




Parallel Sessions

Machine Learning for Imaging and Medical Applications

(organized and chaired by Donglin Zeng, UNC)

Dinggang Shen (UNC)

Machine Learning in Medical Imaging Analysis

Yuanjia Wang (Columbia Univ.)

Support Vector Hazards Machine: A Counting Process Framework for Learning Risk Scores for Censored Outcomes

Ming Yuan (Univ. Wisconsin Madison)

Structured Correlation Detection with Application to Colocalization Analysis in Dual-Channel Fluorescence Microscopic Imaging

High-dimensional Inference

(organized and chaired by Kai Zhang, UNC)

Anru Zhang (Univ. of Wisconsin Madison)

Rate-Optimal Perturbation Bounds for Singular Subspaces with Applications to High-Dimensional Statistics

Han Liu (Princeton)

Combinatorial Inference

Shu Lu (UNC)

Confidence Regions and Intervals for Sparse Penalized Regression Using Variational Inequality Techniques

Topics on High Dimensional Learning and Inference

(organized and chaired by Genevera Allen, Rice Univ.)

Johannes Lederer (Univ. of Washington)

Efficient Feature Selection With Big Data

Weijie Su (Stanford)

Multiple Testing and Adaptive Estimation via the Sorted L-One Norm

Stefan Wager (Stanford)

Causal Inference with Random Forests

Biopharmaceutical Applications

(organized and chaired by Robert Warnock, UCB Biosciences Inc)

Bhargav Reddy (UCB Biosciences Inc)

Predicting Disease State in Crohn’s Patients using Clinical Trial Data

Holger Frohlich (UCB Biosciences Inc)

Re-Use of Randomized Clinical Trials Data for Predictive Modeling in Epilepsy and Systemic Lupus Erythematosus

Scott Clark (Eli Lilly)

Discussion and vision of future developments in pharmaceutical research

June 7 (Tuesday)


Continental Breakfast


Parallel Sessions

The Challenges of machine learning methods and computing tools for large-scale data

(organized by Annie Qu, UIUC; chaired by Yufeng Liu, UNC)

Heping Zhang (Yale Univ.)

Inference with unequal knowledge: nuisance penalized regression, conditional distance correlation, and prior LASSO

Annie Qu (UIUC)

A Group-Specific Recommender System

Yuan Zhang (Univ. of Michigan)

Estimating network edge probabilities by neighborhood smoothing

Inference and Estimation in Statistical Machine Learning

(organized and chaired by Han Liu, Princeton)

Adel Javanmard (USC)

Online Rules for Control of False Discovery Rate

Zhao Ren (Univ. of Pitt.)

Robust Covariance/Scatter Matrix Estimation via Matrix Depth

Zhaoran Wang (Princeton)

Probing the Pareto Frontier of Computational-Statistical Tradeoffs

Network Analysis and Inference tools

(organized by Kai Zhang, UNC; chaired by Mu Zhu, Univ. Waterloo)

Shankar Bhamidi (UNC)

Change Point Detection in Evolving Network Models

Xi Luo (Brown Univ.)

Network Communities and Variable Clustering: A Covariance Matrix Approach

Pingshou Zhong (Michigan State)

Tests for Covariance Structures with High-dimensional Repeated Measurements

Discovery of Features and Patterns

(organized by Cynthia Rudin MIT; chaired by Yiyuan She, Florida State Univ.)

Genevera Allen (Rice Univ.)

Algorithmic Regularization Paths: A New Approach to Variable Selection for High-Dimensional, Highly Correlated Data

Lauren Hannah (Columbia Univ.)

Statistically Summarizing Labeled Text Data

Shawn Mankad (Cornell Univ.)

Single Stage Prediction with Text Data using Dimension Reduction Techniques




Plenary Talk

Susan A. Murphy, Univ. Michigan (chaired by Michael Kosorok, UNC)

Assessing Time-Varying Causal Effect Moderation in Intensive Time-Varying Treatment




Parallel Sessions

Network and Graphical Models

(organized by Hernando Ombao, UC Irvine; chaired by Yunzhang Zhu, Ohio State)

Ali Shojaie (Univ. of Washington)

Network Reconstruction From High Dimensional Ordinary Differential Equations

Lina Lin (Univ. of Washington)

Estimation of High-dimensional Graphical Models using Regularized Score Matching

Shuo Chen (Univ. of Maryland)

Network induced large covariance matrix estimation

Flexible Methods for genomic data

(organized by Yufeng Liu, UNC; chaired by Guan Yu, UNC)

Wei Sun (Fred Hutchinson)

A Two-Step Approach to Estimate the Skeletons of High-Dimensional Directed Acyclic Graphs

Yuying Xie (Michigan State)

Joint Estimation of Multiple Dependent Gaussian Graphical Models with Applications to Mouse Genomics

Dongmei Li (Univ. of Rochester)

An evaluation of statistical methods for RNA-Seq data analysis

Computational Methods in Statistics

(organized and chaired by Sahand Negahban, Yale Univ.)

Constantine Caramanis (UT Austin)

High-dimensional EM algorithm

Sahand Negahban (Yale Univ.)

Restricted Strong Convexity and Weak Submodularity

Garvesh Raskutti (Univ. Wisconsin Madison)

High-dimensional Poisson auto-regressive models for dynamic network modeling

New developments for analyzing complex data

(organized and chaired by Xingye Qiao, SUNY Binghamton)

Xi Chen (NYU)

Optimal Stopping and Worker Selection in Crowdsourcing: an Adaptive Sequential Probability Ratio Test Framework

Jacob Bien (Cornell Univ.)

Lag Structured Modeling for High Dimensional Vector Autoregression

Ganggang Xu (Binghamton Univ.)

A simple averaged post-model-selection confidence interval




Parallel Sessions

Causal Inference

(organized and chaired by Eric Laber, NCSU)

Tyler McCormick (Univ. of Washington)

Standard errors for exchangeable relational arrays

Long Nguyen (Univ. of Michigan)

Bayesian Nonparametric Multilevel Clustering with Group-Level Contexts

Cynthia Rudin (MIT)

Causal Falling Rule Lists

Machine Learning for Structured Data

(organized by Xiaotong Shen, Univ. Minnesota; chaired by Shu Lu, UNC)

Shuheng Zhou (Univ. of Michigan)

High dimensional statistical modeling and estimation with matrix variate data

Xingye Qiao (Binghamton Univ.)

Noncrossing Ordinal Classification

Cun-hui Zhang (Rutgers Univ.)

Nonparametric Shrinkage Estimation

Inference for regularized estimation in high dimensions

(organized and chaired by Ali Shojaie, Univ. Washington)

Max G’Sell (CMU)

Model selection via sequential goodness-of-fit testing

Mladen Kolar (Univ. of Chicago)

Post-Regularization Confidence Bands for High-Dimensional Nonparametric Models with Local Sparsity

Sen Zhao (Univ. of Washington)

High-Dimensional Hypothesis Testing With the Lasso

New learning tools for complex data and beyond

(organized by Yufeng Liu, UNC; chaired by David Pritchard, UNC)

J. Paul Brooks (Virginia Commonwealth Univ.)

Estimating L1-Norm Best-Fit Lines

Chengyong Tang (Temple Univ.)

Precision Matrix Estimation by Inverse Principal Orthogonal Decomposition

Mu Zhu (Univ. of Waterloo)

Networks, Small G Proteins, and Basketball Games


Poster Session
Kiosks will be provided for poster presentations. The boards on the kiosks are 45” x 69”, so a poster of that size or smaller will be fine.

Please check the printable schedule and abstract book above for details.



Speaker: J.S. Marron UNC

June 8 (Wednesday)


Continental Breakfast


Parallel Sessions

Machine learning for precision medicine

(organized by Yufeng Liu, UNC; chaired by Chengyong Tang, Temple University)

Donglin Zeng (UNC)

Estimating Personalized Diagnostic Rules via Weighted Support Vector Machines

Yingqi Zhao (Fred Hutchinson)

Develop Parsimonious and Robust Treatment Strategies for Target Populations

Haoda Fu (Eli Lily)

Personalized Medicine, Machine Learning and Artificial Intelligence: Challenges and Opportunities

New developments on sufficient dimension reduction and envelope estimation

(organized and chaired by Yichao Wu, NCSU)

Andreas Artemiou (Cardiff Univ.)

Robustifying sufficient dimension reduction against inliers and outliers

Zhihua Su (Univ. of Florida)

Groupwise Envelope Models for Imaging Genetic Analysis

Xin Zhang (Florida State)

Some Recent Advances in Envelope Methodology

New Sparse Methods for Regression and Classification

(organized by Hao Helen Zhang; University of Arizona; chaired by Zhigen Zhao, Temple Univ.)

Ning Hao (Univ. of Arizona)

A rotate-and-solve procedure for high dimensional classification

Gen Li (Columbia Univ.)

Supervised Integrative Principal Component Analysis

Sijian Wang (Univ. Wisconsin Madison)

Sparse additive index model for group variable selection




Plenary Talk

Michael R. Kosorok, UNC (chaired by Eric Laber, NCSU)

The Evolution of Data Science and Statistics




Parallel Sessions

Data Integration and Meta Analysis

(organized and chaired by Quefeng Li, UNC)

Haitao Chu (Univ. of Minnesota)

Bayesian Hierarchical Models for Multiple Diagnostic Tests Meta-analysis

Shuangge Ma (Yale Univ.)

Integrating multidimensional omics data for cancer prognosis

Chi Song (Ohio State)

A Bayesian Method for Transcriptomic Meta-analysis – Exploring the Homogeneity and Heterogeneity

Flexible Learning Tools and Applications

(organized and chaired by Yuying Xie, MSU)

Wei Sun (Yahoo)

Provable Sparse Tensor Decomposition and Its Application to Personalized Recommendation

Peng Wang (Univ. of Cincinnati)

Selection by Partitioning the Solution Paths

Tian Zheng (Columbia Univ.)

Topic-adjusted visibility metric for scientific articles

New Sparse Learning Techniques

(organized by Yin Xia, UNC; chaired by Jingxiang Chen UNC)

Botao Hao (Purdue Univ.)

Simultaneous Clustering and Estimation of Multiple Graphical Models

Aaron Molstad (Univ. of Minnesota)

Indirect multivariate response linear regression

Xue Wang (Penn. State)

Folded Concave Penalized Nonconvex Learning via a Modern Optimization Lens




Parallel Sessions

Data Science and Networks: Methodology and Applications

(organized and chaired by Shankar Bhamidi, UNC)

Bailey Fosdick (Colorado Sate)

Multiresolution models for networks

Anand Vidhyashankar (George Mason Univ.)

Implicit Networks in High Dimensional Problems

James Wilson (Univ. San Francisco)

A Significance-based Community Extraction Method for Multilayer Networks

Industrial Applications

(organized by Cynthia Rudin, MIT; chaired by J. Paul Brooks, Virginia Commonwealth Univ.)

Veena Mendiratta (Bell Labs, Alcatel-Lucent)

Anomaly Detection in Wireless Networks using Mobile Phone Data

Matthew Lanham (Virginia Tech)

A Framework for Combining Statistical & Business KPIs for Low-Turn Product Forecasts

C. Bayan Bruss (Accenture)

Predicting Observed GRACE Satellite Groundwater Storage Trends Using Data in 81 Countries

Modern Statistical Learning Methods for Big Data

(organized by Yingying Fan USC; chaired by Siliang Gong UNC)

Will Fithian (UC Berkeley)

Local Case-Control Sampling: Efficient subsampling in imbalanced data sets

Kun Chen (Univ. Connecticut)

Sequential Estimation in Sparse Factor Regression

Yuekai Sun (UC Berkeley)

Feature distributed sparse regression