Joseph Lee Hart

Scientific Machine Learning

Author profile picture

Scientific Machine Learning

joshart@sandia.gov

Sandia National Laboratories, New Mexico
P.O. Box 5800
Albuquerque, NM 87185-1327

Biography

Joseph is interested in quantifying, prioritzing, and mitigating uncertainty in large-scale optimization problems constrained by differential equations. His research spans numerical optimization, sensitivity analysis, inverse problems, optimal experimental design, and scientific machine learning in the service of outer loop analysis. Joseph focuses on finding and exploiting low dimensional structure which arises from taking a wholestic perspective on the scientific computing pipeline from model development to decision-making.

Education

Joseph earned a B.S. in Mathematics from North Carolina State University in 2014, a M.S. in Applied Mathematics from North Carolina State University in 2016, and a Ph.D. in Applied Mathematics with an Interdisciplinary Track in Statistics in 2018, with his dissertation “Extensions of Global Sensitivity Analysis: Theory, Computation, and Application.”

Publications

Isaac Sunseri, Joseph Hart, Alen Alexanderian, Bart van Bloemen Waanders, (2021). Hyper-Differential Sensitivity Analysis of Inverse Problems Governed by PDEs https://doi.org/10.2172/1905697 Publication ID: 77159

Joseph Hart, (2021). Hyper-differential sensitivity analysis in PDE-constrained inverse problems https://www.osti.gov/servlets/purl/1897881 Publication ID: 76771

Elizabeth Newman, Lars Ruthotto, Joseph Hart, Bart van Bloemen Waanders, (2021). Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection SIAM Journal on Mathematics of Data Science https://doi.org/10.1137/20m1359511 Publication ID: 74566

Joseph Hart, Bart van Bloemen Waanders, (2021). Hyper-differential sensitivity analysis for model form error https://doi.org/10.2172/1890383 Publication ID: 75872

Arvind Saibaba, Joseph Hart, Bart van Bloemen Waanders, (2021). Randomized algorithms for generalized singular value decomposition with application to sensitivity analysis Numerical Linear Algebra with Applications https://doi.org/10.1002/nla.2364 Publication ID: 72449

William Reese, Joseph Hart, Bart van Bloemen Waanders, Mauro Perergo, John Jakeman, Arvind Saibaba, (2021). Bedrock Inversion and Hyper Differential Sensitivity Analysis for the Shallow Ice Model https://www.osti.gov/servlets/purl/1889590 Publication ID: 78605

Joseph Hart, (2021). Enabling and interpreting hyper-differential sensitivity analysis for Bayesian inverse problems https://www.osti.gov/servlets/purl/1865768 Publication ID: 78243

Joseph Hart, Steven Gilmore, Pierre Gremaud, Christian Olsen, Jesper Mehlsen, Mette Olufsen, (2021). Classification of orthostatic intolerance through data analytics Medical and Biological Engineering and Computing https://doi.org/10.1007/s11517-021-02314-0 Publication ID: 72982

Joseph Hart, (2021). Hyper-Differential Sensitivity Analysis for Robust Machine Learned Surrogate Models https://doi.org/10.2172/1847611 Publication ID: 77241

Bart van Bloemen Waanders, Joseph Hart, (2020). Hyper-Differential Sensitivity Analysis: Managing High Dimensional Uncertainty in Large-Scale Optimization Problems https://doi.org/10.2172/1877814 Publication ID: 71808

Joseph Hart, (2020). Hyper-Differential Sensitivity Analysis: Managing High Dimensional Uncertainty in Large-Scale Optimization https://www.osti.gov/servlets/purl/1773277 Publication ID: 73151

Isaac Sunseri, Bart van Bloemen Waanders, Joseph Hart, Alen Alexandarian, (2020). Hyper-differential sensitivity analysis of PDE-constrained inverse problems https://www.osti.gov/servlets/purl/1767902 Publication ID: 72708

Joseph Hart, Pierre Gremaud, (2020). Robustness of Sobol? indices to distributional uncertainty https://doi.org/10.1615/Int.J.UncertaintyQuantification.2019030553 Publication ID: 72763

Elizabeth Newman, Lar Ruthotto, Joseph Hart, Bart van Bloemen Waanders, Bart van Bloemen Waanders, (2020). Efficient Training of Neural Network Surrogate Methods with Variable Projection https://www.osti.gov/servlets/purl/1767098 Publication ID: 72698

Isaac Sunseri, Joseph Hart, Alen Alexandarian, Bart van Bloemen Waanders, (2020). Quantifying the relative importance of complimentary parameters in PDE-based inverse problems https://www.osti.gov/servlets/purl/1763861 Publication ID: 70915

Joseph Hart, (2019). Hyper-Differential Sensitivity Analysis to Support Geophysical Inverse Problems https://www.osti.gov/servlets/purl/1643269 Publication ID: 66267

Joseph Hart, (2019). Hyper-differential sensitivity analysis for PDE-constrained optimization: Methods and software https://www.osti.gov/servlets/purl/1641004 Publication ID: 69483

Joseph Hart, Bart van Bloemen Waanders, (2019). Computationally Efficient Parameter Sensitivity Analysis for PDE-Constrained Optimization https://www.osti.gov/servlets/purl/1601532 Publication ID: 67007

Joseph Hart, Bart van Bloemen Waanders, (2019). Global Sensitivity Analysis for PDE-constrained Optimization https://www.osti.gov/servlets/purl/1601533 Publication ID: 67008

Joseph Hart, (2018). Computationally Efficient Parameter Sensitivity Analysis for PDE-Constrained Optimization https://www.osti.gov/servlets/purl/1806909 Publication ID: 60102

Bart van Bloemen Waanders, Joseph Hart, (2018). Sensitivity Analysis for Optimal Control https://www.osti.gov/servlets/purl/1501995 Publication ID: 61108

Jordan Massad, Erin Acquesta, Joseph Hart, (2017). Mathematics and Statistics at Sandia National Laboratories: Perspectives from an Engineering Scientist Analyst and Student Intern https://www.osti.gov/servlets/purl/1511133 Publication ID: 54197

Showing Results. Show More Publications