activity
20172022
most citedPreconditioned training of normalizing flows for variational inference in inverse problems

20 citations · 44 across the 7 of their papers we have counts for

collaborators

14 papers

eess.IV20222 cited

Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging

Rafael Orozco, Mathias Louboutin, Felix J. Herrmann

Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest such as vascularity in cancerous tumor monitoring. When imaging human subjects, geometric rest…

physics.geo-ph2022

Velocity continuation with Fourier neural operators for accelerated uncertainty quantification

Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann

Seismic imaging is an ill-posed inverse problem that is challenged by noisy data and modeling inaccuracies -- due to errors in the background squared-slowness model. Uncertainty qu…

physics.geo-ph2021

Ultra-low memory seismic inversion with randomized trace estimation

Mathias Louboutin, Felix J. Herrmann

Inspired by recent work on extended image volumes that lays the ground for randomized probing of extremely large seismic wavefield matrices, we present a memory frugal and computat…

stat.ML202120 cited

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…

cs.DC2020

Temporal blocking of finite-difference stencil operators with sparse "off-the-grid" sources

George Bisbas, Fabio Luporini, Mathias Louboutin +3

Stencil kernels dominate a range of scientific applications, including seismic and medical imaging, image processing, and neural networks. Temporal blocking is a performance optimi…

physics.geo-ph2020

A dual formulation of wavefield reconstruction inversion for large-scale seismic inversion

Gabrio Rizzuti, Mathias Louboutin, Rongrong Wang +1

Most of the seismic inversion techniques currently proposed focus on robustness with respect to the background model choice or inaccurate physical modeling assumptions, but are not…