no code implementations • 24 May 2024 • Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna, Maarten V. de Hoop
This work introduces a sampling method capable of solving Bayesian inverse problems in function space.
no code implementations • 22 May 2024 • Paul Mayer, Lorenzo Luzi, Ali Siahkoohi, Don H. Johnson, Richard G. Baraniuk
Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution parameters.
1 code implementation • 8 May 2024 • Rafael Orozco, Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann
The benefits of our method requires extra computations but these remain frugal since they are based on physics-hybrid methods and summary statistics.
no code implementations • 20 Dec 2023 • Rafael Orozco, Philipp Witte, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Bas Peters, Felix J. Herrmann
InvertibleNetworks. jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributions.
no code implementations • 4 Jul 2023 • Sina AlEMohammad, Josue Casco-Rodriguez, Lorenzo Luzi, Ahmed Imtiaz Humayun, Hossein Babaei, Daniel LeJeune, Ali Siahkoohi, Richard G. Baraniuk
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models.
1 code implementation • NeurIPS 2023 • Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Since their initial introduction, score-based diffusion models (SDMs) have been successfully applied to solve a variety of linear inverse problems in finite-dimensional vector spaces due to their ability to efficiently approximate the posterior distribution.
1 code implementation • 25 May 2023 • Ali Siahkoohi, Rudy Morel, Randall Balestriero, Erwan Allys, Grégory Sainton, Taichi Kawamura, Maarten V. de Hoop
To perform source separation, we use samples from clusters at multiple timescales obtained via the factorial variational autoencoder as prior information and formulate an optimization problem in the wavelet scattering spectra representation space.
no code implementations • 15 May 2023 • Rafael Orozco, Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann
We validate our method in a controlled setting by applying it to a stylized problem, and observe improved posterior approximations with each iteration.
1 code implementation • 12 Apr 2023 • Mathias Louboutin, Ziyi Yin, Rafael Orozco, Thomas J. Grady II, Ali Siahkoohi, Gabrio Rizzuti, Philipp A. Witte, Olav Møyner, Gerard J. Gorman, Felix J. Herrmann
We present the Seismic Laboratory for Imaging and Modeling/Monitoring (SLIM) open-source software framework for computational geophysics and, more generally, inverse problems involving the wave-equation (e. g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations.
no code implementations • 6 Mar 2023 • Rafael Orozco, Mathias Louboutin, Ali Siahkoohi, Gabrio Rizzuti, Tristan van Leeuwen, Felix Herrmann
Our method combines physics-informed methods and data-driven methods to accelerate the reconstruction of the final image.
1 code implementation • 27 Jan 2023 • Ali Siahkoohi, Rudy Morel, Maarten V. de Hoop, Erwan Allys, Grégory Sainton, Taichi Kawamura
Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator.
1 code implementation • 1 Nov 2022 • Lorenzo Luzi, Daniel LeJeune, Ali Siahkoohi, Sina AlEMohammad, Vishwanath Saragadam, Hossein Babaei, Naiming Liu, Zichao Wang, Richard G. Baraniuk
We study the interpolation capabilities of implicit neural representations (INRs) of images.
no code implementations • 21 Oct 2022 • Lorenzo Luzi, Paul M Mayer, Josue Casco-Rodriguez, Ali Siahkoohi, Richard G. Baraniuk
As implied by its name, Boomerang local sampling involves adding noise to an input image, moving it closer to the latent space, and then mapping it back to the image manifold through a partial reverse diffusion process.
2 code implementations • 24 Jul 2022 • Ali Siahkoohi, Gabrio Rizzuti, Rafael Orozco, Felix J. Herrmann
While generic and applicable to other inverse problems, by means of a linearized seismic imaging example, we show that our correction step improves the robustness of amortized variational inference with respect to changes in the number of seismic sources, noise variance, and shifts in the prior distribution.
no code implementations • 5 Jul 2022 • Ali Siahkoohi, Michael Chinen, Tom Denton, W. Bastiaan Kleijn, Jan Skoglund
Our numerical experiments show that supplementing the convolutional encoder of a neural speech codec with Transformer speech embeddings yields a speech codec with a bitrate of $600\,\mathrm{bps}$ that outperforms the original neural speech codec in synthesized speech quality when trained at the same bitrate.
1 code implementation • 27 Mar 2022 • Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann
As such, the main contribution of this work is a survey-specific Fourier neural operator surrogate to velocity continuation that maps seismic images associated with one background model to another virtually for free.
1 code implementation • 27 Mar 2022 • Ziyi Yin, Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann
We show that we can accurately use a Fourier neural operator as a proxy for the fluid-flow simulator for a fraction of the computational cost.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Rafael Orozco, Ali Siahkoohi, Gabrio Rizzuti, Tristan van Leeuwen, Felix Johan Herrmann
For many ill-posed inverse problems, such as photoacoustic imaging, the uncertainty of the solution is highly affected by measurement noise and data incompleteness (due, for example, to limited aperture).
1 code implementation • 10 Oct 2021 • Ali Siahkoohi, Gabrio Rizzuti, Felix J. Herrmann
We propose to use techniques from Bayesian inference and deep neural networks to translate uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as horizon tracking.
1 code implementation • 13 Jun 2021 • Mathias Louboutin, Ali Siahkoohi, Rongrong Wang, Felix J. Herrmann
Thanks to the combination of state-of-the-art accelerators and highly optimized open software frameworks, there has been tremendous progress in the performance of deep neural networks.
3 code implementations • 13 Apr 2021 • Ali Siahkoohi, Felix J. Herrmann
To arrive at this result, we train the NF on pairs of low- and high-fidelity migrated images.
2 code implementations • pproximateinference AABI Symposium 2021 • Ali Siahkoohi, Gabrio Rizzuti, Mathias Louboutin, Philipp A. Witte, Felix J. Herrmann
Obtaining samples from the posterior distribution of inverse problems with expensive forward operators is challenging especially when the unknowns involve the strongly heterogeneous Earth.
no code implementations • 15 Jul 2020 • Ali Siahkoohi, Gabrio Rizzuti, Philipp A. Witte, Felix J. Herrmann
In inverse problems, we often have access to data consisting of paired samples $(x, y)\sim p_{X, Y}(x, y)$ where $y$ are partial observations of a physical system, and $x$ represents the unknowns of the problem.
2 code implementations • 16 Apr 2020 • Gabrio Rizzuti, Ali Siahkoohi, Philipp A. Witte, Felix J. Herrmann
Uncertainty quantification for full-waveform inversion provides a probabilistic characterization of the ill-conditioning of the problem, comprising the sensitivity of the solution with respect to the starting model and data noise.
1 code implementation • 15 Apr 2020 • Mi Zhang, Ali Siahkoohi, Felix J. Herrmann
Because different frequency slices share information, we propose the use the method of transfer training to make our approach computationally more efficient by warm starting the training with CNN weights obtained from a neighboring frequency slices.
1 code implementation • 14 Apr 2020 • Ali Siahkoohi, Gabrio Rizzuti, Felix J. Herrmann
The chief advantage of this approach is that the updates for the CNN weights do not involve the modeling operator, and become relatively cheap.
Geophysics Image and Video Processing
1 code implementation • 1 Apr 2020 • Ali Siahkoohi, Gabrio Rizzuti, Felix J. Herrmann
In this paper, we focus on how UQ trickles down to horizon tracking for the determination of stratigraphic models and investigate its sensitivity with respect to the imaging result.
2 code implementations • 13 Jan 2020 • Ali Siahkoohi, Gabrio Rizzuti, Felix J. Herrmann
Uncertainty quantification is essential when dealing with ill-conditioned inverse problems due to the inherent nonuniqueness of the solution.
1 code implementation • 27 Sep 2019 • Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann
One proxy of incomplete physics is an inaccurate discretization of Laplacian in simulation of wave equation via finite-difference method.
no code implementations • NeurIPS Workshop Deep_Invers 2019 • Felix J. Herrmann, Ali Siahkoohi, Gabrio Rizzuti
We outline new approaches to incorporate ideas from deep learning into wave-based least-squares imaging.