arXiv subjects

Malena Sabate Landman

Publications and source records attributed to Malena Sabate Landman.

5 recordsLinked to original sources

arXiv2024

Efficient hyperparameter estimation in Bayesian inverse problems using sample average approximation

In Bayesian inverse problems, it is common to consider several hyperparameters that define the prior and the noise model that must be estimated from the data. In particular, we are interested in linear inverse problems with additive Gaussian noise and Gaussian priors defined using Matérn covariance models. In this case, we estimate the hyperparameters using the maximum a posteriori (MAP) estimate of the marginalized posterior distribution. However, this is a computationally intensive task since it involves computing log determinants. To address this challenge, we consider a stochastic average approximation (SAA) of the objective function and use the preconditioned Lanczos method to compute efficient approximations of the function and gradient evaluations. We propose a new preconditioner that can be updated cheaply for new values of the hyperparameters and an approach to compute approximations of the gradient evaluations, by reutilizing information from the function evaluations. We demonstrate the performance of our approach on static and dynamic seismic tomography problems.

math.NA↗

arXiv2023

Augmented Flexible Krylov Subspace methods with applications to Bayesian inverse problems

This paper presents two new augmented flexible (AF)-Krylov subspace methods, AF-GMRES and AF-LSQR, to compute solutions of large-scale linear discrete ill-posed problems that can be modeled as the sum of two independent random variables, exhibiting smooth and sparse stochastic characteristics respectively. Following a Bayesian modelling approach, this corresponds to adding a covariance-weighted quadratic term and a sparsity enforcing $\ell_1$ term in the original least-squares minimization scheme. To handle the $\ell_1$ regularization term, the proposed approach constructs a sequence approximating quadratic problems that are partially solved using augmented flexible Krylov-Tikhonov methods. Compared to other traditional methods used to solve this minimization problem, such as those based on iteratively reweighted norm schemes, the new algorithms build a single (augmented, flexible) approximation (Krylov) subspace that encodes information about the different regularization terms through adaptable "preconditioning". The solution space is then expanded as soon as a new problem within the sequence is defined. This also allows for the regularization parameters to be chosen on-the-fly at each iteration. Compared to most recent work on generalized flexible Krylov methods, our methods offer theoretical assurance of convergence and a more stable numerical performance. The efficiency of the new methods is shown through a variety of experiments, including a synthetic image deblurring problem, a synthetic atmospheric transport problem, and fluorescence molecular tomography reconstructions using both synthetic and real-world experimental data.

math.NA↗

arXiv2023

Latent-space disentanglement with untrained generator networks for the isolation of different motion types in video data

Isolating different types of motion in video data is a highly relevant problem in video analysis. Applications can be found, for example, in dynamic medical or biological imaging, where the analysis and further processing of the dynamics of interest is often complicated by additional, unwanted dynamics, such as motion of the measurement subject. In this work, it is empirically shown that a representation of video data via untrained generator networks, together with a specific technique for latent space disentanglement that uses minimal, one-dimensional information on some of the underlying dynamics, allows to efficiently isolate different, highly non-linear motion types. In particular, such a representation allows to freeze any selection of motion types, and to obtain accurate independent representations of other dynamics of interest. Obtaining such a representation does not require any pre-training on a training data set, i.e., all parameters of the generator network are learned directly from a single video.

eess.IV↗

arXiv2022

On Krylov Methods for Large Scale CBCT Reconstruction

Krylov subspace methods are a powerful family of iterative solvers for linear systems of equations, which are commonly used for inverse problems due to their intrinsic regularization properties. Moreover, these methods are naturally suited to solve large-scale problems, as they only require matrix-vector products with the system matrix (and its adjoint) to compute approximate solutions, and they display a very fast convergence. Even if this class of methods has been widely researched and studied in the numerical linear algebra community, its use in applied medical physics and applied engineering is still very limited. e.g. in realistic large-scale Computed Tomography (CT) problems, and more specifically in Cone Beam CT (CBCT). This work attempts to breach this gap by providing a general framework for the most relevant Krylov subspace methods applied to 3D CT problems, including the most well-known Krylov solvers for non-square systems (CGLS, LSQR, LSMR), possibly in combination with Tikhonov regularization, and methods that incorporate total variation (TV) regularization. This is provided within an open source framework: the Tomographic Iterative GPU-based Reconstruction (TIGRE) toolbox, with the idea of promoting accessibility and reproducibility of the results for the algorithms presented. Finally, numerical results in synthetic and real-world 3D CT applications (medical CBCT and μ-CT datasets) are provided to showcase and compare the different Krylov subspace methods presented in the paper, as well as their suitability for different kinds of problems.

math.NA↗

arXiv2019

Adaptive Regularization Parameter Choice Rules for Large-Scale Problems

This paper derives a new class of adaptive regularization parameter choice strategies that can be effectively and efficiently applied when regularizing large-scale linear inverse problems by combining standard Tikhonov regularization and projection onto Krylov subspaces of increasing dimension (computed by the Golub-Kahan bidiagonalization algorithm). The success of this regularization approach heavily depends on the accurate tuning of two parameters (namely, the Tikhonov parameter and the dimension of the projection subspace): these are simultaneously set using new strategies that can be regarded as special instances of bilevel optimization methods, which are solved by using a new paradigm that interlaces the iterations performed to project the Tikhonov problem (lower-level problem) with those performed to apply a given parameter choice rule (higher-level problem). The discrepancy principle, the GCV, the quasi-optimality criterion, and Regińska criterion can all be adapted to work in this framework. The links between Gauss quadrature and Golub-Kahan bidiagonalization are exploited to prove convergence results for the discrepancy principle, and to give insight into the behavior of the other considered regularization parameter choice rules. Several numerical tests modeling inverse problems in imaging show that the new parameter choice strategies lead to regularization methods that are reliable, and intrinsically simpler and cheaper than other strategies already available in the literature.

math.NA↗