Opening Workshop: August 12-16, 2019

** Deadline for applications was June 12, 2019 **

After applying to a SAMSI workshop, our organizers/staff will review your information. Applicants will be notified about the decision within two weeks after the deadline for submitting the application. If you have not received a notification by that time, please send inquiries to


This workshop will take place at Gross Hall on the campus of Duke University.


The SAMSI Deep Learning program will bring together mathematical, statistical, and computer scientists interested in understanding the theoretical capabilities and limitations of deep learning methodology. This workshop will feature overview talks that introduce the basic concepts of deep networks (including convolutional neural networks, recursive neural networks, generative adversarial networks, and various kinds of autoencoders). Additionally, there will be a series of talks that highlight recent research in this area. On Thursday, participants will break out into working groups, and develop plans for their semester of work on these topics. On Friday morning, the leaders of the working groups will share those plans with all of the workshop participants. The workshop ends at noon on Friday.

Confirmed speakers for this event include:

** Notice of Consent **

SAMSI values the proprietary and intellectual property of our participants. The materials presented at our various workshops and programs are in high demand by event participants and the applied mathematics and statistics community that comprise our audience. Therefore, we encourage all of our invited speakers to share their materials, as appropriate, in order to pass along the valuable research that is being done in your field of study and is a focus of this event. In addition, unless SAMSI is give written approval from our speakers we ARE NOT authorized to share the materials presented at this event.

Please click HERE to complete a SAMSI Consent form for this event. SAMSI appreciates your time and willingness to share this valuable content with others and we hope you enjoy this event!

For any questions or concerns about our consent policy, please contact us at:

** Planning for this event is ongoing **

Schedule and Supporting Media

Printed Schedule

Monday, May 12, 2019
Ahmadieh Family Auditorium, Gross Hall, Rm 107, Duke University, Durham, NC

Time Description Speaker Slides
8:30am Registration
8:50-9:00am Welcome David Banks, Duke University and Director, SAMSI
9:00-9:40am To be determined Xiaoming Huo, Georgia Institute of Technology
9:40-10:20am Admissibility of Solution Estimators for Stochastic Optimization Amitabh Basu, Johns Hopkins University
10:20-10:50am COFFEE
10:50-11:30am Statistical and Computational Guarantees of EM with Random Initialization Harrison Zhou, Yale University
11:30am-12:10pm Adversarial Risk bounds via Function Transformation Poh-Ling Loh, University of Wisconsin
12:10-1:40pm Lunch on own
1:40-2:20pm To be determined Jianqing Fan, Princeton University
2:20-3:00pm Horseshoe Regularization for Machine Learning in Complex and Deep Models Anindya Bhadra, Purdue University
3:00-3:30pm COFFEE
3:30-4:10pm To be determined Veronika Rockova, University of Chicago
4:10-4:50pm Deep Compositional Spatial Models Andrew Zammit Mangion, University of Woolongong, Australia
4:50-5:30pm Training DNN with Dynamic SMD Shih-Kang Chao, University of Missouri
5:30-7:00pm Posters and Reception

Tuesday, August 13, 2019
Ahmadieh Family Auditorium, Gross Hall, Rm 107, Duke University, Durham, NC

Time Description Speaker Slides
9:00-9:40am On Adversarial Learning Larry Carin, Duke University
9:40-10:20am To be determined Zuofeng Shang, University of Indiana
10:20-10:50am COFFEE
10:50-11:30am Improving Generative Models Junier Oliva, University of North Carolina at Chapel Hill
11:30am-12:10pm Learning to Solve Inverse Problems in Imaging Rebecca Willet, University of Chicago
12:10-1:40pm Lunch on own
1:40-2:20pm An Adaptively Weighted Stochastic Gradient MCMC Algorithm for Global Optimization in Deep Learning Faming Liang, Purdue University
2:20-3:00pm Information Geometric and Topological Approaches to Deep Learning Wyatt Bridgman and Sorin Mitran, University of North Carolina at Chapel Hill
3:00-3:30pm COFFEE
3:30-4:10pm To be determined Bianca Dumitrascu, Princeton University and SAMSI
4:10-4:50pm Neural Network Density Estimation Deborshee Sen, Duke University and SAMSI
4:50-5:30pm Complexity Bounds for Deep Learning Networks via the Probabilistic Method Jason Klusowski, Rutgers University

Wednesday, August 14, 2019
Ahmadieh Family Auditorium, Gross Hall, Rm 107, Duke University, Durham, NC

Time Description Speaker Slides
9:00-9:40am Statistical Inference for Online Decision Making via Stochastic Gradient Descent Rui Song, N.C. State University
9:40-10:20am Modern Statistical Theory Inspired by Deep Learning Guang Cheng, Purdue University
10:20-10:50am COFFEE
10:50-11:30am Deep ReLU Networks Viewed as a Statistical Method Johannes Schmidt-Hieber, University of Twente
11:30am-12:10pm Robust Hypothesis Testing Using Wasserstein Uncertainty Sets Yao Xie, Georgia Institute of Technology
12:10-1:40pm Lunch on own
1:40-2:20pm ProxSARAH Algorithms for Stochastic Composite Nonconvex Optimization Quoc Tran-Dinh, University of North Carolina at Chapel Hill
2:20-3:00pm Deep Models for Improved Topic Recovery Deanna Needell, UCLA
3:00-3:30pm COFFEE
3:30-4:10pm Group-equivariant Representation by Jointly Decomposed Convolution Xiuyuan Cheng, Duke University
4:10-4:50pm To be determined Guanghui (George) Lan, Georgia Institute of Technology
4:50-5:30pm Working Group Formation

Thursday, August 15, 2019
Ahmadieh Family Auditorium,  Gross Hall, Breakout Rooms: 304B, 318, 324, 352
Social Sciences Bldg: 107
Old Chemistry Bldg: 003,119,123
Duke University, Durham, NC

Time Description
9:00am-5:30pm Working Groups Meet in Breakout Rooms
12:30-1:30pm Lunch on own

Friday, August 16, 2019
Ahmadieh Family Auditorium Gross Hall, Rm 107, Duke University, Durham, NC

Time Description
9:00-10:30am Working Group Leaders provide description of research plans
10:30-11:00am COFFEE
11:00-11:45am Working Group Leaders provide description of research plans
11:45am-12:00pm Closing Remarks
12:15pm Shuttle to RDU

Questions: email