Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs T O’Leary-Roseberry, U Villa, P Chen, O Ghattas Computer Methods in Applied Mechanics and Engineering 388, 114199, 2022 | 62 | 2022 |
Projected Stein variational Newton: A fast and scalable Bayesian inference method in high dimensions P Chen, K Wu, J Chen, T O'Leary-Roseberry, O Ghattas Advances in Neural Information Processing Systems 32, 2019 | 61 | 2019 |
Learning high-dimensional parametric maps via reduced basis adaptive residual networks T O’Leary-Roseberry, X Du, A Chaudhuri, JRRA Martins, K Willcox, ... Computer Methods in Applied Mechanics and Engineering 402, 115730, 2022 | 25* | 2022 |
Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning T O'Leary-Roseberry, P Chen, U Villa, O Ghattas Journal of Computational Physics 496, 112555, 2024 | 24 | 2024 |
Large-scale Bayesian optimal experimental design with derivative-informed projected neural network K Wu, T O’Leary-Roseberry, P Chen, O Ghattas Journal of Scientific Computing 95 (1), 30, 2023 | 21* | 2023 |
Inexact Newton methods for stochastic nonconvex optimization with applications to neural network training T O'Leary-Roseberry, N Alger, O Ghattas arXiv preprint arXiv:1905.06738, 2019 | 21 | 2019 |
Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems L Cao, T O'Leary-Roseberry, PK Jha, JT Oden, O Ghattas Journal of Computational Physics 486, 112104, 2023 | 18 | 2023 |
Low rank saddle free Newton: A scalable method for stochastic nonconvex optimization T O'Leary-Roseberry, N Alger, O Ghattas arXiv preprint arXiv:2002.02881, 2020 | 12* | 2020 |
Efficient PDE-constrained optimization under high-dimensional uncertainty using derivative-informed neural operators D Luo, T O'Leary-Roseberry, P Chen, O Ghattas arXiv preprint arXiv:2305.20053, 2023 | 10 | 2023 |
Efficient and dimension independent methods for neural network surrogate construction and training TF O'Leary-Roseberry The University of Texas at Austin, 2020 | 7 | 2020 |
hippyflow: Dimension reduced surrogate construction for parametric PDE maps in Python T O’Leary-Roseberry, U Villa DOI: https://doi. org/10.5281/zenodo 4608729, 2021 | 5* | 2021 |
Learning optimal aerodynamic designs through multi-fidelity reduced-dimensional neural networks X Du, JR Martins, T O’Leary-Roseberry, A Chaudhuri, O Ghattas, ... AIAA SCITECH 2023 Forum, 0334, 2023 | 4 | 2023 |
Ill-posedness and optimization geometry for nonlinear neural network training T O'Leary-Roseberry, O Ghattas arXiv preprint arXiv:2002.02882, 2020 | 4 | 2020 |
Efficient geometric Markov chain Monte Carlo for nonlinear Bayesian inversion enabled by derivative-informed neural operators L Cao, T O'Leary-Roseberry, O Ghattas arXiv preprint arXiv:2403.08220, 2024 | | 2024 |
Workshop Report 23w5129 Scientific Machine Learning B Keith, T O’Leary-Roseberry, L Lu, S Mishra, Z Mao | | 2023 |
Transport-Based Variational Bayesian Methods for Learning from Data D Bigoni, J Chen, P Chen, O Ghattas, Y Marzouk, T O’Leary–Roseberry, ... dimensions 3, 4, 0 | | |