36 citations · 155 across the 14 of their papers we have counts for
14 papers
Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods
Thomas O'Leary-Roseberry, Raghu Bollapragada
We consider minimizing finite-sum and expectation objective functions via Hessian-averaging based subsampled Newton methods. These methods allow for gradient inexactness and have f…
Inference of Heterogeneous Material Properties via Infinite-Dimensional Integrated DIC
Joseph Kirchhoff, Dingcheng Luo, Thomas O'Leary-Roseberry +1
We present a scalable and efficient framework for the inference of spatially-varying parameters of continuum materials from image observations of their deformations. Our goal is th…
A note on the relationship between PDE-based precision operators and Matérn covariances
Umberto Villa, Thomas O'Leary-Roseberry
The purpose of this technical note is to summarize the relationship between the marginal variance and correlation length of a Gaussian random field with Matérn covariance and the c…
Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems
Lianghao Cao, Thomas O'Leary-Roseberry, Omar Ghattas
We propose an operator learning approach to accelerate geometric Markov chain Monte Carlo (MCMC) for solving infinite-dimensional Bayesian inverse problems (BIPs). While geometric…
Efficient PDE-Constrained optimization under high-dimensional uncertainty using derivative-informed neural operators
Dingcheng Luo, Thomas O'Leary-Roseberry, Peng Chen +1
We propose a novel machine learning framework for solving optimization problems governed by large-scale partial differential equations (PDEs) with high-dimensional random parameter…
Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems
Lianghao Cao, Thomas O'Leary-Roseberry, Prashant K. Jha +2
We explore using neural operators, or neural network representations of nonlinear maps between function spaces, to accelerate infinite-dimensional Bayesian inverse problems (BIPs)…
Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
Thomas O'Leary-Roseberry, Peng Chen, Umberto Villa +1
We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to…
Large-scale Bayesian optimal experimental design with derivative-informed projected neural network
Keyi Wu, Thomas O'Leary-Roseberry, Peng Chen +1
We address the solution of large-scale Bayesian optimal experimental design (OED) problems governed by partial differential equations (PDEs) with infinite-dimensional parameter fie…
Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks
Thomas O'Leary-Roseberry, Xiaosong Du, Anirban Chaudhuri +3
We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs a…
Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
Thomas O'Leary-Roseberry, Umberto Villa, Peng Chen +1
Many-query problems, arising from uncertainty quantification, Bayesian inversion, Bayesian optimal experimental design, and optimization under uncertainty-require numerous evaluati…
Ill-Posedness and Optimization Geometry for Nonlinear Neural Network Training
Thomas O'Leary-Roseberry, Omar Ghattas
In this work we analyze the role nonlinear activation functions play at stationary points of dense neural network training problems. We consider a generic least squares loss functi…
Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization
Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas
In modern deep learning, highly subsampled stochastic approximation (SA) methods are preferred to sample average approximation (SAA) methods because of large data sets as well as g…
Inexact Newton Methods for Stochastic Nonconvex Optimization with Applications to Neural Network Training
Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas
We study stochastic inexact Newton methods and consider their application in nonconvex settings. Building on the work of [R. Bollapragada, R. H. Byrd, and J. Nocedal, IMA Journal o…
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
Peng Chen, Keyi Wu, Joshua Chen +2
We propose a fast and scalable variational method for Bayesian inference in high-dimensional parameter space, which we call projected Stein variational Newton (pSVN) method. We exp…