Thomas O'Leary-Roseberry

Orcid: 0000-0002-8938-7074

According to our database1, Thomas O'Leary-Roseberry authored at least 15 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Derivative-Informed Neural Operator: An efficient framework for high-dimensional parametric derivative learning.
J. Comput. Phys., January, 2024

SOUPy: Stochastic PDE-constrained optimization under high-dimensional uncertainty in Python.
J. Open Source Softw., 2024

Inference of Heterogeneous Material Properties via Infinite-Dimensional Integrated DIC.
CoRR, 2024

Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods.
CoRR, 2024

A note on the relationship between PDE-based precision operators and Matérn covariances.
CoRR, 2024

Efficient geometric Markov chain Monte Carlo for nonlinear Bayesian inversion enabled by derivative-informed neural operators.
CoRR, 2024

2023
Large-Scale Bayesian Optimal Experimental Design with Derivative-Informed Projected Neural Network.
J. Sci. Comput., April, 2023

Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems.
J. Comput. Phys., 2023

Efficient PDE-Constrained optimization under high-dimensional uncertainty using derivative-informed neural operators.
CoRR, 2023

2022
Derivative-informed projected neural network for large-scale Bayesian optimal experimental design.
CoRR, 2022

2021
Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data.
CoRR, 2021

2020
Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs.
CoRR, 2020

Ill-Posedness and Optimization Geometry for Nonlinear Neural Network Training.
CoRR, 2020

Low Rank Saddle Free Newton: Algorithm and Analysis.
CoRR, 2020

2019
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019


  Loading...