Search Results for author: Deep Ray

Found 14 papers, 2 papers with code

Learning WENO for entropy stable schemes to solve conservation laws

no code implementations21 Mar 2024 Philip Charles, Deep Ray

In the present work, we propose a variant of the SP-WENO, termed as Deep Sign-Preserving WENO (DSP-WENO), where a neural network is trained to learn the WENO weighting strategy.

Learning end-to-end inversion of circular Radon transforms in the partial radial setup

no code implementations27 Aug 2023 Deep Ray, Souvik Roy

We present a deep learning-based computational algorithm for inversion of circular Radon transforms in the partial radial setup, arising in photoacoustic tomography.

Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty

no code implementations8 Jun 2023 Deep Ray, Javier Murgoitio-Esandi, Agnimitra Dasgupta, Assad A. Oberai

The cWGAN developed in this work differs from earlier versions in that its critic is required to be 1-Lipschitz with respect to both the inferred and the measurement vectors and not just the former.

Generative Adversarial Network

Deep Learning and Computational Physics (Lecture Notes)

no code implementations3 Jan 2023 Deep Ray, Orazio Pinti, Assad A. Oberai

These notes were compiled as lecture notes for a course developed and taught at the University of the Southern California.

Variationally Mimetic Operator Networks

no code implementations26 Sep 2022 Dhruv Patel, Deep Ray, Michael R. A. Abdelmalik, Thomas J. R. Hughes, Assad A. Oberai

The application of the VarMiON to a canonical elliptic PDE and a nonlinear PDE reveals that for approximately the same number of network parameters, on average the VarMiON incurs smaller errors than a standard DeepONet and a recently proposed multiple-input operator network (MIONet).

The efficacy and generalizability of conditional GANs for posterior inference in physics-based inverse problems

no code implementations15 Feb 2022 Deep Ray, Harisankar Ramaswamy, Dhruv V. Patel, Assad A. Oberai

In this work, we train conditional Wasserstein generative adversarial networks to effectively sample from the posterior of physics-based Bayesian inference problems.

Bayesian Inference

Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors

no code implementations6 Jul 2021 Dhruv V Patel, Deep Ray, Assad A Oberai

Specifically, we demonstrate how using the approximate distribution learned by a Generative Adversarial Network (GAN) as a prior in a Bayesian update and reformulating the resulting inference problem in the low-dimensional latent space of the GAN, enables the efficient solution of large-scale Bayesian inverse problems.

Bayesian Inference Generative Adversarial Network +1

Bayesian Inference in Physics-Driven Problems with Adversarial Priors

no code implementations23 Oct 2020 Dhruv V Patel, Deep Ray, Harisankar Ramaswamy, Assad Oberai

Generative adversarial networks (GANs) have found multiple applications in the solution of inverse problems in science and engineering.

Bayesian Inference

Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

4 code implementations13 Aug 2020 Kjetil O. Lye, Siddhartha Mishra, Deep Ray, Praveen Chandrasekhar

We present a novel active learning algorithm, termed as iterative surrogate model optimization (ISMO), for robust and efficient numerical approximation of PDE constrained optimization problems.

Active Learning Model Optimization

On the approximation of rough functions with deep neural networks

no code implementations13 Dec 2019 Tim De Ryck, Siddhartha Mishra, Deep Ray

Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions.

Data Compression

Constraint-Aware Neural Networks for Riemann Problems

no code implementations29 Apr 2019 Jim Magiera, Deep Ray, Jan S. Hesthaven, Christian Rohde

Neural networks are increasingly used in complex (data-driven) simulations as surrogates or for accelerating the computation of classical surrogates.

Deep learning observables in computational fluid dynamics

3 code implementations7 Mar 2019 Kjetil O. Lye, Siddhartha Mishra, Deep Ray

Under the assumption that the underlying neural networks generalize well, we prove that the deep learning MC and QMC algorithms are guaranteed to be faster than the baseline (quasi-) Monte Carlo methods.

Efficient Neural Network Uncertainty Quantification

Cannot find the paper you are looking for? You can Submit a new open access paper.