Searcharxiv⌕ Search

arXiv subjects

Benedikt Wirth

Publications and source records attributed to Benedikt Wirth.

At least 37 records · Page 2Linked to original sources
arXiv2022

Duality in branched transport and urban planning

In recent work arXiv:2109.07820 we have shown the equivalence of the widely used nonconvex (generalized) branched transport problem with a shape optimization problem of a street or railroad network, known as (generalized) urban planning problem. The argument was solely based on an explicit construction and characterization of competitors. In the current article we instead analyse the dual perspective associated with both problems. In more detail, the shape optimization problem involves the Wasserstein distance between two measures with respect to a metric depending on the street network. We show a Kantorovich$\unicode{x2013}$Rubinstein formula for Wasserstein distances on such street networks under mild assumptions. Further, we provide a Beckmann formulation for such Wasserstein distances under assumptions which generalize our previous result in arXiv:2109.07820. As an application we then give an alternative, duality-based proof of the equivalence of both problems under a growth condition on the transportation cost, which reveals that urban planning and branched transport can both be viewed as two bilinearly coupled convex optimization problems.

math.OC↗
arXiv2021

Formulation of branched transport as geometry optimization

The branched transport problem, a popular recent variant of optimal transport, is a non-convex and non-smooth variational problem on Radon measures. The so-called urban planning problem, on the contrary, is a shape optimization problem that seeks the optimal geometry of a street or pipe network. We show that the branched transport problem with concave cost function is equivalent to a generalized version of the urban planning problem. Apart from unifying these two different models used in the literature, another advantage of the urban planning formulation for branched transport is that it provides a more transparent interpretation of the overall cost by separation into a transport (Wasserstein-1-distance) and a network maintenance term, and it splits the problem into the actual transportation task and a geometry optimization.

math.OC↗
arXiv2021

Convex relaxation of discrete vector-valued optimization problems

We consider a class of infinite-dimensional optimization problems in which a distributed vector-valued variable should pointwise almost everywhere take values from a given finite set $\mathcal{M}\subset\mathbb{R}^m$. Such hybrid discrete--continuous problems occur in, e.g., topology optimization or medical imaging and are challenging due to their lack of weak lower semicontinuity. To circumvent this difficulty, we introduce as a regularization term a convex integral functional with an integrand that has a polyhedral epigraph with vertices corresponding to the values of $\mathcal{M}$; similar to the $L^1$ norm in sparse regularization, this "vector multibang penalty" promotes solutions with the desired structure while allowing the use of tools from convex optimization for the analysis as well as the numerical solution of the resulting problem. We show well-posedness of the regularized problem and analyze stability properties of its solution in a general setting. We then illustrate the approach for three specific model optimization problems of broader interest: optimal control of the Bloch equation, optimal control of an elastic deformation, and a multimaterial branched transport problem. In the first two cases, we derive explicit characterizations of the penalty and its generalized derivatives for a concrete class of sets $\mathcal{M}$. For the third case, we discuss the algorithmic computation of these derivatives for general sets. These derivatives are then used in a superlinearly convergent semismooth Newton method applied to a sequence of regularized optimization problems. We illustrate the behavior of this approach for the three model problems with numerical examples.

math.OC↗
arXiv2021

Learning low bending and low distortion manifold embeddings

Autoencoders are a widespread tool in machine learning to transform high-dimensional data into a lowerdimensional representation which still exhibits the essential characteristics of the input. The encoder provides an embedding from the input data manifold into a latent space which may then be used for further processing. For instance, learning interpolation on the manifold may be simplified via the new manifold representation in latent space. The efficiency of such further processing heavily depends on the regularity and structure of the embedding. In this article, the embedding into latent space is regularized via a loss function that promotes an as isometric and as flat embedding as possible. The required training data comprises pairs of nearby points on the input manifold together with their local distance and their local Frechet average. This regularity loss functional even allows to train the encoder on its own. The loss functional is computed via a Monte Carlo integration which is shown to be consistent with a geometric loss functional defined directly on the embedding map. Numerical tests are performed using image data that encodes different data manifolds. The results show that smooth manifold embeddings in latent space are obtained. These embeddings are regular enough such that interpolation between not too distant points on the manifold is well approximated by linear interpolation in latent space.

cs.LG↗
arXiv2021

Elastic 3D-2D Image Registration

We propose a method to non-rigidly align a three-dimensional (3D) volumetric image with a two-dimensional (2D) planar image representing a projection of the deformed volume. The application in mind comes from biological studies in which 2D intravital microscopy videos of living tissue are recorded, after which the tissue is excised and a more detailed 3D volume microscopy is performed. Coregistration of both data sets allows to combine the temporal (but 2D) information with more detailed spatial 3D information. Our approach is variational and uses a hyperelastic deformation regularization, as is appropriate for biological material. As a particular feature, the out of plane deformation is estimated based on the out of focus blur inside the 2D microscopy image. The approach becomes computationally feasible through the use of a coarse-to-fine optimization strategy and higher order optimization methods.

math.OC↗
arXiv2020

Quartic $L^p$-convergence of cubic Riemannian splines

We prove quartic convergence of cubic spline interpolation for curves into Riemannian manifolds as the grid size of the interpolation grid tends to zero. In contrast to cubic spline interpolation in Euclidean space, where this result is classical, the interpolation operator is no longer linear. Still, concepts from the linear setting may be generalized to the Riemannian case, where we try to use intrinsic Riemannian formulations and avoid charts as much as possible.

math.NA↗
arXiv2020

General transport problems with branched minimizers as functionals of 1-currents with prescribed boundary

A prominent model for transportation networks is branched transport, which seeks the optimal transportation scheme to move material from a given initial to a final distribution. The cost of the scheme encodes a higher transport efficiency the more mass is moved together, which automatically leads to optimal transportation networks with a hierarchical branching structure. The two major existing model formulations, either using mass fluxes (vector-valued measures) or patterns (probabilities on the space of particle paths), are rather different. Once their equivalence was established, the analysis of optimal networks could rest on both. The transportation cost of classical branched transport is a fractional power of the transported mass, and several model properties and proof techniques build on its strict concavity. We generalize the model and its analysis to the most general class of reasonable transportation costs, essentially increasing, subadditive functions. This requires several modifications or new approaches. In particular, for the equivalence between mass flux and pattern formulation it turns out advantageous to resort to a description via 1-currents, an intuition which already Xia exploited. In addition, some already existing arguments are given a more concise and perhaps simpler form. The analysis includes the well-posedness, a metrization and a length space property of the model cost, the equivalence between the different model formulations, as well as a few network properties.

math.CA↗
arXiv2020

Entropic regularization of continuous optimal transport problems

We analyze continuous optimal transport problems in the so-called Kantorovich form, where we seek a transport plan between two marginals that are probability measures on compact subsets of Euclidean space. We consider the case of regularization with the negative entropy with respect to the Lebesgue measure, which has attracted attention because it can be solved by the very simple Sinkhorn algorithm. We first analyze the regularized problem in the context of classical Fenchel duality and derive a strong duality result for a predual problem in the space of continuous functions. However, this problem may not admit a minimizer, which prevents obtaining primal-dual optimality conditions. We then show that the primal problem is naturally analyzed in the Orlicz space of functions with finite entropy in the sense that the entropically regularized problem admits a minimizer if and only if the marginals have finite entropy. We then derive a dual problem in the corresponding dual space, for which existence can be shown by purely variational arguments and primal-dual optimality conditions can be derived. For marginals that do not have finite entropy, we finally show Gamma-convergence of the regularized problem with smoothed marginals to the original Kantorovich problem.

math.OC↗
arXiv2020

An adaptive finite element approach for lifted branched transport problems

We consider so-called branched transport and variants thereof in two space dimensions. In these models one seeks an optimal transportation network for a given mass transportation task. In two space dimensions, they are closely connected to Mumford--Shah-type image processing problems, which in turn can be related to certain higher-dimensional convex optimization problems via so-called functional lifting. We examine the relation between these different models and exploit it to solve the branched transport model numerically via convex optimization. To this end we develop an efficient numerical treatment based on a specifically designed class of adaptive finite elements. This method allows the computation of finely resolved optimal transportation networks despite the high dimensionality of the convex optimization problem and its complicated set of nonlocal constraints. In particular, by design of the discretization the infinite set of constraints reduces to a finite number of inequalities.

math.NA↗
arXiv2019

A mathematical model for cell polarization in zebrafish primordial germ cells

Blebs are cell protrusions generated by local membrane-cortex detachments followed by expansion of the plasma membrane. Blebs are formed by some migrating cells, for example primordial germ cells of the zebrafish. While blebs occur randomly at each part of the membrane in unpolarized cells, a polarization process guarantees the occurrence of blebs at a preferential site and thereby facilitates migration towards a specified direction. Little is known about the factors involved in development and maintenance of a polarized state, yet recent studies revealed the influence of an intracellular flow and the stabilizing role of the membrane-cortex linker molecule Ezrin. Based on this information, we develop and analyse a coupled bulk-surface model describing a potential cellular mechanism by which a bleb could be induced at a controlled site. The model rests upon intracellular Darcy flow and a diffusion-advection-reaction system, describing the temporal evolution from an unpolarized to a stable polarized Ezrin distribution. We prove the well-posedness of the mathematical model and show that simulations qualitatively correspond to experimental observations, suggesting that indeed the interaction of an intracellular flow with membrane proteins can be the cause of the cell polarization.

math.AP↗
arXiv2019

Consistent Curvature Approximation on Riemannian Shape Spaces

We describe how to approximate the Riemann curvature tensor as well as sectional curvatures on possibly infinite-dimensional shape spaces that can be thought of as Riemannian manifolds. To this end, we extend the variational time discretization of geodesic calculus presented in Rumpf and Wirth (2015), which just requires an approximation of the squared Riemannian distance that is typically easy to compute. First we obtain first order discrete covariant derivatives via a Schild's ladder type discretization of parallel transport. Second order discrete covariant derivatives are then computed as nested first order discrete covariant derivatives. These finally give rise to an approximation of the curvature tensor. First and second order consistency are proven for the approximations of the covariant derivative and the curvature tensor. The findings are experimentally validated on two-dimensional surfaces embedded in $\mathbb{R}^3$. Furthermore, as a proof of concept the method is applied to the shape space of triangular meshes, and discrete sectional curvature indicatrices are computed on low-dimensional vector bundles.

math.NA↗
arXiv2019

Dynamic Cell Imaging in PET with Optimal Transport Regularization

We propose a novel dynamic image reconstruction method from PET listmode data that could be particularly suited to tracking single or small numbers of cells. In contrast to conventional PET reconstruction our method combines the information from all detected events not only to reconstruct the dynamic evolution of the radionuclide distribution, but also to improve the reconstruction at each single time point by enforcing temporal consistency. This is achieved via optimal transport regularization where in principle, among all possible temporally evolving radionuclide distributions consistent with the PET measurement, the one is chosen with least kinetic motion energy. The reconstruction is found by convex optimization so that there is no dependence on the initialization of the method. We study its behaviour on simulated data of a human PET system and demonstrate its robustness even in settings with very low radioactivity. In contrast to previously reported cell tracking algorithms, our technique is oblivious to the number of tracked cells. Without any additional complexity one or multiple cells can be reconstructed, and the model automatically determines the number of particles. For instance, four radiolabelled cells moving at a velocity of 3.1 mm/s and a PET recorded count rate of 1.1 cps (for each cell) could be simultaneously tracked with a tracking accuracy of 5.3 mm inside a simulated human body.

cs.CV↗
arXiv2019

Green's function for Poisson's equation and the EEG equation with Neumann boundary condition on $n$-balls

We provide an elementary derivation of the Green's function for Poisson's equation with Neumann boundary data on balls of arbitrary dimension, which was recently found in [Sadybekov et al., Eurasian Math. J. 7(2):100-105, 2016]. The underlying idea consists of first computing the Green's function for the electroencephalography (EEG) equation (Poisson's equation with dipole right-hand side) and then deriving the Green's function for Poisson's equation from that.

math.AP↗
arXiv2018

Approximation of rectifiable $1$-currents and weak-$\ast$ relaxation of the $h$-mass

Based on Smirnov's decomposition theorem we prove that every rectifiable $1$-current $T$ with finite mass $\mathbb{M}(T)$ and finite mass $\mathbb{M}(\partial T)$ of its boundary $\partial T$ can be approximated in mass by a sequence of rectifiable $1$-currents $T_n$ with polyhedral boundary $\partial T_n$ and $\mathbb{M}(\partial T_n)$ no larger than $\mathbb{M}(\partial T)$. Using this result we can compute the relaxation of the $h$-mass for polyhedral $1$-currents with respect to the joint weak-$\ast$ convergence of currents and their boundaries. We obtain that this relaxation coincides with the usual $h$-mass for normal currents. This shows that the concepts of so-called generalized branched transport and the $h$-mass are equivalent.

math.FA↗
arXiv2018

Phase field approximations of branched transportation problems

In branched transportation problems mass has to be transported from a given initial distribution to a given final distribution, where the cost of the transport is proportional to the transport distance, but subadditive in the transported mass. As a consequence, mass transport is cheaper the more mass is transported together, which leads to the emergence of hierarchically branching transport networks. We here consider transport costs that are piecewise affine in the transported mass with N affine segments, in which case the resulting network can be interpreted as a street network composed of N different types of streets. In two spatial dimensions we propose a phase field approximation of this street network using N phase fields and a function approximating the mass flux through the network. We prove the corresponding $Γ$-convergence and show some numerical simulation results.

math.OC↗
arXiv2018

Phase field models for two-dimensional branched transportation problems

We analyse the following inverse problem. Given a nonconvex functional (from a specific, but quite general class) of normal, codimension-1 currents (which in two spatial dimensions can be interpreted as transportation networks), find the potential of a phase field energy which approximates the given functional. We prove existence of a solution as well as its characterization via a linear deconvolution problem. We also provide an explicit formula that allows to approximate the solution arbitrarily well in the supremum norm.

math.OC↗
arXiv2018

A Framework for Wasserstein-1-Type Metrics

We propose a unifying framework for generalising the Wasserstein-1 metric to a discrepancy measure between nonnegative measures of different mass. This generalization inherits the convexity and computational efficiency from the Wasserstein-1 metric, and it includes several previous approaches from the literature as special cases. For various specific instances of the generalized Wasserstein-1 metric we furthermore demonstrate their usefulness in applications by numerical experiments.

math.OC↗