Picture for Thomas O'Leary-Roseberry

Thomas O'Leary-Roseberry

LazyDINO: Fast, scalable, and efficiently amortized Bayesian inversion via structure-exploiting and surrogate-driven measure transport

Add code
Nov 19, 2024
Viaarxiv icon

Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods

Add code
Aug 14, 2024
Viaarxiv icon

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

Add code
Mar 13, 2024
Viaarxiv icon

Efficient PDE-Constrained optimization under high-dimensional uncertainty using derivative-informed neural operators

Add code
May 31, 2023
Viaarxiv icon

Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems

Add code
Oct 06, 2022
Figure 1 for Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
Figure 2 for Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
Figure 3 for Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
Figure 4 for Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
Viaarxiv icon

Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning

Add code
Jun 23, 2022
Figure 1 for Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
Figure 2 for Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
Figure 3 for Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
Figure 4 for Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
Viaarxiv icon

Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data

Add code
Dec 14, 2021
Figure 1 for Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data
Figure 2 for Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data
Figure 3 for Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data
Figure 4 for Adaptive Projected Residual Networks for Learning Parametric Maps from Sparse Data
Viaarxiv icon

Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs

Add code
Nov 30, 2020
Figure 1 for Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
Figure 2 for Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
Figure 3 for Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
Figure 4 for Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
Viaarxiv icon

Ill-Posedness and Optimization Geometry for Nonlinear Neural Network Training

Add code
Feb 07, 2020
Viaarxiv icon

Low Rank Saddle Free Newton: Algorithm and Analysis

Add code
Feb 07, 2020
Figure 1 for Low Rank Saddle Free Newton: Algorithm and Analysis
Figure 2 for Low Rank Saddle Free Newton: Algorithm and Analysis
Figure 3 for Low Rank Saddle Free Newton: Algorithm and Analysis
Figure 4 for Low Rank Saddle Free Newton: Algorithm and Analysis
Viaarxiv icon