Workshop on the Interface of Statistics and Optimization (WISO)

This workshop was held at the Penn Pavilion (Level 2), Duke University, Durham, NC


The integration and cross-fertilization between statistics and optimization is urgent and productive. Traditionally, optimization has merely been used as a tool to compute numerical solutions for statistical problems, while optimization theory and algorithms have rarely supported statistical techniques. This compartmental approach is proving to be non-optimal. More and more statistical tools are being developed by borrowing strengths from optimization, while optimization is looking to statistics for new insights, speed and robustness.

This workshop will bring together researchers who are pioneers in the synergy of statistics and optimization. It will serve SAMSI’s mission to forge a synthesis of the statistical sciences and the applied mathematical sciences with disciplinary science to confront the very hardest and most important data- and model-driven scientific challenges. The workshop will also address contemporary issues with potentially significant impact in industrial applications.

Schedule and Speakers:

Confirmed Speakers currently include:

Schedule and Supporting Media

Speaker Titles/Abstracts

Workshop Poster Titles

Wednesday, February, 8 2017

Penn Pavilion, Duke University Campus, Durham, NC

Description Speaker Slides Videos
Welcome & Introduction Richard Smith, SAMSI Director; Ilse Ipsen, SAMSI Assoc. Director  
On Statistical Inferences via Convex Optimization Arkadi Nemirovski, Georgia Institute of Technology    video
Old, New, Borrowed, and Blue in the Marriage of Statistics and Optimization Margaret Wright, Courant Institute of Mathematics    video
Phase Retrieval and Analog to Digital Compression Yonina Eldar, Technion-Israel Institute of Technology – ISR    video
Parameter Identification for Dynamical Systems with Structured Uncertainty John Burns, Virginia Tech    video

Thursday, February 9, 2017

Penn Pavilion, Duke University Campus, Durham, NC

Description Speaker Slides Videos
The Road to Exascale and Legacy Software for Dense Linear Algebra Jack Dongarra, University of Tennessee    video
Tensors and their Eigenvectors Bernd Sturmfels, University of California – Berkeley    video
Statistics Meets Optimization: Fast Randomized Algorithms for Large Data Sets Martin Wainwright, University of California – Berkeley     video
Sparse Learning and Distributed PCA with Control of Statistical Errors and Computing Resources Jianqing Fan, Princeton University    video
On Gradient-Based Optimization: Accelerated, Distributed, Asynchronous and Stochastic Michael Jordan, University of California – Berkeley    video

Friday, February 10, 2017

Penn Pavilion, Duke University Campus, Durham, NC

Description Speaker Slides Videos
Randomness in Coordinate Descent Stephen Wright, University of Wisconsin-Madison    video
Model Discrimination and Parameter Estimation for Complex Reactive Systems Larry Biegler, Carnegie Mellon University     video
Statistical Inference of Empirical Estimates of Stochastic Programs Alexander Shapiro, Georgia Institute of Technology video

Questions: email