Agenda Oct 2 – 4, 2024

Schedule Day 1 – Wednesday Oct 2, 2024:

Time	Speaker	Institution	Talk Title
8:45	Registration
9:15	Welcome
9:30	Francisco Villaescusa	Flatiron Institute, Simons Foundation	Machine Learning for Cosmology: Opportunities and Challenges
10:00	Aleksandra Pachalieva	Los Alamos National Lab	Sparse, Distributed, Automatic Jacobians for Large-Scale Scientific Machine Learning
10:30	Coffee
11:00	Tom Seidl	Sandia National Laboratories	Calibration of Hybrid Constitutive Models from Full-field Data
11:30	John Jakeman	Sandia National Laboratories	Linear Least Squares Learning of Non-linear Operators
12:00	Lunch & TACC Vislab
1:30	Michael Lindsey	University of California, Berkeley	Column and Row Subset Selection using Nuclear Scores: Algorithms and Theory for Nyström Approximation, CUR Decomposition, and Graph Laplacian Reduction
2:00	Ramin Bostanabad	University of California, Irvine	Gaussian Processes: from Solving Nonlinear PDEs to Operator Learning
2:30	Ramansh Sharma	University of Utah	Ensemble and Mixture-of-Experts DeepONets for Operator Learning
3:00	Coffee
3:30	Stella Offner, Leonardo Zepeda-Núñez, Tim Wildey	University of Texas at Austin, Google, Sandia National Laboratories	Career Panel
4:30	Asghar Jadoon	University of Texas at Austin	Input Specific Neural Networks
4:45	Ryan Farell	University of Texas at Austin	Memory Efficient RL or Three-Phase Flow
5:00	End of Day

Time	Speaker	Institution	Talk Title
8:45	Registration
9:00	Deirdre Shoemaker	University of Texas at Austin	Challenges in Using Gravitational Waves to make Discoveries
9:30	Anthony Gruber	Sandia National Laboratories	Property-preserving Machine Learning for Metriplectic Systems
10:00			2 minute poster talks
10:30	Coffee
11:00	Michael Sacks	University of Texas at Austin	Neural Network Finite Element Approaches for Cardiac Simulations
11:30	Ruda Zhang	University of Houston	Stochastic Subspace via Probabilistic PCA to Characterize and Correct Model Error
12:00	Nicole Aretz	University of Texas at Austin	Multifidelity Uncertainty Quantification for Sea Level Contributions of Ice Sheets
12:30	Lunch and Poster Session
2:30	Nishant Panda & Yen Ting Lin	Los Alamos National Lab	Generative Modeling for High Dimensional Sampling: Liouville Flow Importance Sampler
3:00	Coffee
3:30	Leonardo Zepeda-Núñez	Google	Recent Advances in Probabilistic SciML
4:00	Ravi Patel	Sandia National Laboratories	A Novel Ensemble Approach to Uncertainty Quantification in Operator Learning
4:30	Yi Wang	University of Texas at Austin	Learning Dynamical Surrogates with Optimal Flow Control
4:45	End of Day

Time	Speaker	Institution	Talk Title
9:00	Qiang Sun	University of Chicago	Can AI Models Predict Gray Swan Events?
9:30	Jan Fuhg	University of Texas at Austin	Scientific Machine Learning for Discovering Interpretable Material Models
10:00	Yinan Zhao	University of Texas at Austin	Deep Learning for Earth-Like Planet Detection in Presence of Stellar Activity
10:30	Coffee
11:00	Matthias Chung	Emory University	Paired Autoencoders for Inverse Problems
11:30	Luke McLennan	University of Texas at Austin	Learning Hamiltonian Dynamics from Noisy Data: A Stable and Generalizable Duelling Framework
11:45	Hai Nguyen	University of Texas at Austin	A Model-Constrained Discontinuous Galerkin Network (DGNet) for Solving Compressible Euler Equations with Out-of-Distribution Scenarios
12:00	Closing Remarks