Session 1

8:30 am - 8:55 am

Roger Ghanem, University of Southern California

Data-driven Sampling and Prediction on Manifolds

8:55 am - 9:20 am

Michael Shields, Johns Hopkins University

How Much Data do I Really Need to Conduct Probabilistic UQ?

Bob Moser, University of Texas at Austin

Validating the Reliability of Predictions Based on Unreliable Models

10:15 am - 10:40 am

Paris Perdikaris, MIT

Data-driven Modeling and Optimization with Probabilistic Multi-fidelity Surrogates

10:40 am - 11:05 am

Rick Archibald, Oak Ridge National Laboratory

Sparse Sampling Methods for Large Scale Experimental Data

11:05 am - 11:30 am

Kevin Carlberg, Sandia National Laboratories

Reducing Nonlinear Dynamical Systems via Model Reduction and Machine Learning

2:25 pm - 2:50 pm

Nathan Kutz, University of Washington

Data-driven Discovery of Governing Equations in the Engineering and Physical Sciences

2:50 pm - 3:15 pm

David Stracuzzi, Sandia National Laboratories

Uncertainty Quantification for Machine Learning and Statistical Models

3:15 pm - 3:40 pm

Youssef Marzouk, Massachusetts Institute of Technology

Low-dimensional Couplings for Bayesian Inference

4:10 pm - 4:35 pm

Daniele Schiavazzi, University of Notre Dame

A Generalized Multi-resolution Expansion for Uncertainty Propagation with Application to Cardiovascular Modeling,  Part 1,

Part 2

4:35 pm - 5:00 pm

Paul Barbone, Boston University

Efficiently Computing Covariance of Parameter Estimates in Inverse Problems

5:00 pm - 5:25 pm

Tan Bui, University of Texas at Austin

A Randomized Misfit Approach for Data-Driven PDE-constrained Bayesian Inverse Problems

8:15 am - 8:40 am

J. Tinsley Oden, University of Texas at Austin

Selection and Validation of Predictive Models of Tumor Growth and Cancer Therapies

8:40 am - 9:05 am

Alberto Figueroa, University of Michigan

A Reduced-Order Kalman Filtering Approach for Data-driven Parameter Estimation in Arterial Hemodynamics

9:05 am - 9:30 am

Ben Peherstorfer, University of Wisconsin

Multifidelity Methods for Uncertainty Propagation and Rare Event Simulation

9:30 am - 9:55 am

Qiqi Wang, Massachusetts Institute of Technology

When Does an Accurate Model Lead to a Predictive Simulation?

10:25 am - 10:50 am

Omar Ghattas, University of Texas at Austin

Scalable Methods for Optimal Control of Systems Governed by PDEs with Random Coefficient Fields

10:50 am - 11:15 am

Jon Freund, University of Illinois at Urbana-Champaign

Adjoint-based Sensitivity in Turbulent Combustion Simulation

11:15 am - 11:40 am

Mohammad Khalil, Sandia National Laboratories

Data-Driven Bayesian Model Selection: Parameter Space Dimension Reduction using Automatic Relevance Determination Priors

11:40 am - 12:05 pm

Karthik Duraisamy, University of Michigan

A Paradigm for Data-driven Predictive Modeling Using Field Inversion and Machine Learning