202 citations · 339 across the 14 of their papers we have counts for
15 papers
InvertibleNetworks.jl: A Julia package for scalable normalizing flows
Rafael Orozco, Philipp Witte, Mathias Louboutin +4
InvertibleNetworks.jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributio…
Learned multiphysics inversion with differentiable programming and machine learning
Mathias Louboutin, Ziyi Yin, Rafael Orozco +7
We present the Seismic Laboratory for Imaging and Modeling/Monitoring (SLIM) open-source software framework for computational geophysics and, more generally, inverse problems invol…
SciAI4Industry -- Solving PDEs for industry-scale problems with deep learning
Philipp A. Witte, Russell J. Hewett, Kumar Saurabh +2
Solving partial differential equations with deep learning makes it possible to reduce simulation times by multiple orders of magnitude and unlock scientific methods that typically…
Model-Parallel Fourier Neural Operators as Learned Surrogates for Large-Scale Parametric PDEs
Thomas J. Grady, Rishi Khan, Mathias Louboutin +5
Fourier neural operators (FNOs) are a recently introduced neural network architecture for learning solution operators of partial differential equations (PDEs), which have been show…
Accelerating innovation with software abstractions for scalable computational geophysics
Mathias Louboutin, Philipp A. Witte, Ali Siahkoohi +4
We present the SLIM (https://github.com/slimgroup) open-source software framework for computational geophysics, and more generally, inverse problems based on the wave-equation (e.g…
Preconditioned training of normalizing flows for variational inference in inverse problems
Ali Siahkoohi, Gabrio Rizzuti, Mathias Louboutin +2
Obtaining samples from the posterior distribution of inverse problems with expensive forward operators is challenging especially when the unknowns involve the strongly heterogeneou…