Thomas O'Leary-Roseberry

Thomas O'Leary-Roseberry

Computational Mathematician | Optimization, Simulation and Operator Learning.

Publications

Preprints

Shape Derivative-Informed Neural Operators with Application to Risk-Averse Shape Optimization,
Xindi Gong, Dingcheng Luo, Thomas O’Leary-Roseberry, Ruanui Nicholson and Omar Ghattas
Submitted [preprint] [BibTeX]

Performance of Neural and Polynomial Operator Surrogates,
Josephine Westermann, Benno Huber, Thomas O’Leary-Roseberry and Jakob Zech
Submitted [preprint]

[BibTeX] 
@misc{westermann2026performance,
  title={Performance of Neural and Polynomial Operator Surrogates},
  author={Westermann, Josephine and Huber, Benno and O'Leary-Roseberry, Thomas and Zech, Jakob},
  year={2026},
  eprint={2604.00689},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2604.00689}
}

Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization,
Boyuan Yao, Dingcheng Luo, Lianghao Cao, Nikola Kovachki, Thomas O’Leary-Roseberry and Omar Ghattas
Submitted [preprint]

[BibTeX] 
@misc{yao2025derivative,
  title={Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization},
  author={Yao, Boyuan and Luo, Dingcheng and Cao, Lianghao and Kovachki, Nikola and O'Leary-Roseberry, Thomas and Ghattas, Omar},
  year={2025},
  eprint={2512.14086},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2512.14086}
}

Dimension reduction for derivative-informed operator learning: An analysis of approximation errors,
Dingcheng Luo, Thomas O’Leary-Roseberry, Peng Chen, Omar Ghattas
In review at Journal of Machine Learning Research [preprint]

[BibTeX] 
@misc{luo2025dimension,
  title={Dimension Reduction for Derivative-Informed Operator Learning: An Analysis of Approximation Errors},
  author={Luo, Dingcheng and O'Leary-Roseberry, Thomas and Chen, Peng and Ghattas, Omar},
  year={2025},
  eprint={2504.08730},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2504.08730}
}

Inference of Heterogeneous Material Properties via Infinite-Dimensional Integrated DIC
Joseph Kirchhoff, Dingcheng Luo, Thomas O’Leary-Roseberry and Omar Ghattas
In review at Journal of Computational Physics [preprint] [BibTeX]

Journal Articles

Inverse Mapping for Airfoil Optimization Using Multifidelity Reduced-Order Neural Networks
Xiaosong Du, Joaquim R. R. A. Martins and Thomas O’Leary-Roseberry
Journal of Aircraft (2026) [Journal of Aircraft paper]

[BibTeX] 
@article{du2026inverse,
  title={Inverse Mapping for Airfoil Optimization Using Multifidelity Reduced-Order Neural Networks},
  author={Du, Xiaosong and Martins, Joaquim R. R. A. and O'Leary-Roseberry, Thomas},
  journal={Journal of Aircraft},
  year={2026},
  doi={10.2514/1.C038635},
  url={https://arc.aiaa.org/doi/abs/10.2514/1.C038635}
}

Fast Finite-Sum Optimization via Cyclically-Sampled Hessian Averaging Methods
Thomas O’Leary-Roseberry and Raghu Bollapragada
Mathematical Programming (2026) [MP Paper]

[BibTeX] 
@article{olearyroseberry2026fast,
  title={Fast Finite-Sum Optimization via Cyclically-Sampled Hessian Averaging Methods},
  author={O'Leary-Roseberry, Thomas and Bollapragada, Raghu},
  journal={Mathematical Programming},
  year={2026},
  doi={10.1007/s10107-026-02354-0},
  url={https://link.springer.com/article/10.1007/s10107-026-02354-0}
}

LazyDINO: Fast, Scalable, and Efficiently Amortized Bayesian Inversion via Structure-Exploiting and Surrogate-Driven Measure Transport
Lianghao Cao, Joshua Chen, Michael Brennan, Thomas O’Leary-Roseberry, Youssef Marzouk and Omar Ghattas
Journal of Machine Learning Research (2026) [JMLR Paper]

[BibTeX] 
@article{cao2026lazydino,
  title={LazyDINO: Fast, Scalable, and Efficiently Amortized Bayesian Inversion via Structure-Exploiting and Surrogate-Driven Measure Transport},
  author={Cao, Lianghao and Chen, Joshua and Brennan, Michael and O'Leary-Roseberry, Thomas and Marzouk, Youssef and Ghattas, Omar},
  journal={Journal of Machine Learning Research},
  year={2026},
  volume={27},
  url={https://www.jmlr.org/papers/v27/25-0858.html}
}

Verification and Validation for Trustworthy Scientific Machine Learning
John Jakeman, Lorena Barba, Joaquim R. R. A. Martins, Thomas O’Leary-Roseberry
Machine Learning: Science and Technology (2026) [MLST Paper]

[BibTeX] 
@article{jakeman2026verification,
  title={Verification and Validation for Trustworthy Scientific Machine Learning},
  author={Jakeman, John and Barba, Lorena and Martins, Joaquim R. R. A. and O'Leary-Roseberry, Thomas},
  journal={Machine Learning: Science and Technology},
  year={2026},
  doi={10.1088/2632-2153/ae59ec},
  url={https://iopscience.iop.org/article/10.1088/2632-2153/ae59ec}
}

Efficient PDE-constrained optimization under high-dimensional uncertainty using derivative-informed neural operators
Dingcheng Luo, Thomas O’Leary-Roseberry, Peng Chen and Omar Ghattas
SIAM Journal on Scientific Computing (2025) [SISC Paper] [BibTeX]

Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems
Lianghao Cao, Thomas O’Leary-Roseberry, and Omar Ghattas
Journal of Machine Learning Research (2025) [JMLR Paper]

[BibTeX] 
@article{cao2025derivative,
  title={Derivative-Informed Neural Operator Acceleration of Geometric MCMC for Infinite-Dimensional Bayesian Inverse Problems},
  author={Cao, Lianghao and O'Leary-Roseberry, Thomas and Ghattas, Omar},
  journal={Journal of Machine Learning Research},
  year={2025},
  volume={26},
  url={https://www.jmlr.org/papers/volume26/24-0745/24-0745.pdf}
}

Scientific Machine Learning: A Symbiosis
Brendan Keith, Thomas O’Leary-Roseberry, Benjamin Sanderse, Robert Scheichl and Bart van Bloemen Waanders
Foundations of Data Science (2025) [FoDS article]

[BibTeX] 
@article{keith2025scientific,
  title={Scientific Machine Learning: A Symbiosis},
  author={Keith, Brendan and O'Leary-Roseberry, Thomas and Sanderse, Benjamin and Scheichl, Robert and van Bloemen Waanders, Bart},
  journal={Foundations of Data Science},
  year={2025},
  doi={10.3934/fods.2024051},
  url={https://www.aimsciences.org/article/doi/10.3934/fods.2024051}
}

SOUPy: Stochastic PDE-constrained optimization under high-dimensional uncertainty in Python
Dingcheng Luo, Peng Chen, Thomas O’Leary-Roseberry, Umberto Villa and Omar Ghattas
Journal of Open Source Software (2024) [GitHub] [JOSS Paper]

[BibTeX] 
@article{luo2024soupy,
  title={SOUPy: Stochastic PDE-Constrained Optimization Under High-Dimensional Uncertainty in Python},
  author={Luo, Dingcheng and Chen, Peng and O'Leary-Roseberry, Thomas and Villa, Umberto and Ghattas, Omar},
  journal={Journal of Open Source Software},
  year={2024},
  doi={10.21105/joss.06101},
  url={https://joss.theoj.org/papers/10.21105/joss.06101}
}

Derivative-Informed Neural Operator: An efficient framework for high-dimensional parametric derivative learning
Thomas O’Leary-Roseberry, Peng Chen, Umberto Villa and Omar Ghattas
Journal of Computational Physics (2024) [JCP paper] [preprint]

[BibTeX] 
@article{olearyroseberry2024derivative,
  title={Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning},
  author={O'Leary-Roseberry, Thomas and Chen, Peng and Villa, Umberto and Ghattas, Omar},
  journal={Journal of Computational Physics},
  year={2024},
  url={https://www.sciencedirect.com/science/article/pii/S0021999123006502}
}

Residual-based error correction of neural operator accelerated infinite-dimensional Bayesian inverse problems
Lianghao Cao, Thomas O’Leary-Roseberry, Prashant Jha, J. Tinsley Oden and Omar Ghattas
Journal of Computational Physics (2023) [JCP paper] [preprint]

[BibTeX] 
@article{cao2023residual,
  title={Residual-Based Error Correction of Neural Operator Accelerated Infinite-Dimensional Bayesian Inverse Problems},
  author={Cao, Lianghao and O'Leary-Roseberry, Thomas and Jha, Prashant and Oden, J. Tinsley and Ghattas, Omar},
  journal={Journal of Computational Physics},
  year={2023},
  url={https://www.sciencedirect.com/science/article/pii/S0021999123001997}
}

Large-scale Bayesian optimal experimental design with derivative-informed projected neural networks
Keyi Wu, Thomas O’Leary-Roseberry, Peng Chen and Omar Ghattas
Journal of Scientific Computing (2023) [JSC paper] [preprint]

[BibTeX] 
@article{wu2023large,
  title={Large-Scale Bayesian Optimal Experimental Design with Derivative-Informed Projected Neural Networks},
  author={Wu, Keyi and O'Leary-Roseberry, Thomas and Chen, Peng and Ghattas, Omar},
  journal={Journal of Scientific Computing},
  year={2023},
  doi={10.1007/s10915-023-02145-1},
  url={https://link.springer.com/article/10.1007/s10915-023-02145-1}
}

Learning high-dimensional parametric maps via reduced basis adaptive residual networks
Thomas O’Leary-Roseberry, Xiaosong Du, Anirban Chaudhuri, Joaquim R. R. A. Martins, Karen Willcox and Omar Ghattas
Computer Methods in Applied Mechanics and Engineering (2022) [CMAME paper] [preprint]

[BibTeX] 
@article{olearyroseberry2022learning,
  title={Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks},
  author={O'Leary-Roseberry, Thomas and Du, Xiaosong and Chaudhuri, Anirban and Martins, Joaquim R. R. A. and Willcox, Karen and Ghattas, Omar},
  journal={Computer Methods in Applied Mechanics and Engineering},
  year={2022},
  url={https://www.sciencedirect.com/science/article/pii/S0045782522006855}
}

Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs
Thomas O’Leary-Roseberry, Umberto Villa, Peng Chen and Omar Ghattas
Computer Methods in Applied Mechanics and Engineering (2022) [CMAME paper] [preprint]

[BibTeX] 
@article{olearyroseberry2022derivative,
  title={Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs},
  author={O'Leary-Roseberry, Thomas and Villa, Umberto and Chen, Peng and Ghattas, Omar},
  journal={Computer Methods in Applied Mechanics and Engineering},
  year={2022},
  url={https://www.sciencedirect.com/science/article/pii/S0045782521005302}
}

Conference Proceedings

Neural Operator-Enabled Aerodynamic Load Estimation for Hypersonics
Julie Pham, Patrick J. Blonigan, Thomas O’Leary-Roseberry, Omar Ghattas and Karen E. Willcox
AIAA SciTech Forum 2026 [SciTech paper]

[BibTeX] 
@inproceedings{pham2026neural,
  title={Neural Operator-Enabled Aerodynamic Load Estimation for Hypersonics},
  author={Pham, Julie and Blonigan, Patrick J. and O'Leary-Roseberry, Thomas and Ghattas, Omar and Willcox, Karen E.},
  booktitle={AIAA SCITECH 2026 Forum},
  year={2026},
  doi={10.2514/6.2026-1210},
  url={https://arc.aiaa.org/doi/10.2514/6.2026-1210}
}

Improving neural network efficiency with multifidelity and dimensionality reduction techniques
Vignesh Sella, Thomas O’Leary-Roseberry, Xiaosong Du, Mengwu Guo, Joaquim R. R. A. Martins, Omar Ghattas, Karen Willcox and Anirban Chaudhuri
AIAA SciTech Forum 2025 [SciTech paper]

[BibTeX] 
@inproceedings{sella2025improving,
  title={Improving Neural Network Efficiency with Multifidelity and Dimensionality Reduction Techniques},
  author={Sella, Vignesh and O'Leary-Roseberry, Thomas and Du, Xiaosong and Guo, Mengwu and Martins, Joaquim R. R. A. and Ghattas, Omar and Willcox, Karen and Chaudhuri, Anirban},
  booktitle={AIAA SciTech Forum 2025},
  year={2025},
  doi={10.2514/6.2025-2807},
  url={https://arc.aiaa.org/doi/abs/10.2514/6.2025-2807}
}

Learning optimal aerodynamic designs through multi-fidelity reduced-dimensional neural networks
Xiaosong Du, Joaquim R. R. A. Martins, Thomas O’Leary-Roseberry, Anirban Chaudhuri, Omar Ghattas and Karen Willcox
AIAA SciTech Forum 2023 [SciTech paper]

[BibTeX] 
@inproceedings{du2023learning,
  title={Learning Optimal Aerodynamic Designs Through Multi-Fidelity Reduced-Dimensional Neural Networks},
  author={Du, Xiaosong and Martins, Joaquim R. R. A. and O'Leary-Roseberry, Thomas and Chaudhuri, Anirban and Ghattas, Omar and Willcox, Karen},
  booktitle={AIAA SciTech Forum 2023},
  year={2023},
  doi={10.2514/6.2023-0334},
  url={https://arc.aiaa.org/doi/10.2514/6.2023-0334}
}

Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
Peng Chen, Keyi Wu, Joshua Chen, Thomas O’Leary Roseberry and Omar Ghattas
Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) [NeurIPS paper]

[BibTeX] 
@inproceedings{chen2019projected,
  title={Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions},
  author={Chen, Peng and Wu, Keyi and Chen, Joshua and O'Leary-Roseberry, Thomas and Ghattas, Omar},
  booktitle={Advances in Neural Information Processing Systems},
  year={2019},
  url={http://papers.neurips.cc/paper/9649-projected-stein-variational-newton-a-fast-and-scalable-bayesian-inference-method-in-high-dimensions.pdf}
}

Technical Reports

A note on the relationship between PDE-based precision operators and Matérn covariances
Umberto Villa and Thomas O’Leary-Roseberry [arXiv]

[BibTeX] 
@misc{villa2024note,
  title={A Note on the Relationship Between PDE-Based Precision Operators and Matern Covariances},
  author={Villa, Umberto and O'Leary-Roseberry, Thomas},
  year={2024},
  eprint={2407.00471},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2407.00471}
}

PhD Thesis

Efficient and dimension independent methods for neural network surrogate construction and training
PhD Dissertation, The University of Texas at Austin (2020) [link]

[BibTeX] 
@phdthesis{olearyroseberry2020efficient,
  title={Efficient and Dimension Independent Methods for Neural Network Surrogate Construction and Training},
  author={O'Leary-Roseberry, Thomas},
  school={The University of Texas at Austin},
  year={2020},
  url={https://repositories.lib.utexas.edu/items/53c3b97d-0961-4143-99b4-07d9a8319f19}
}