Publications related to On the Well-Posedness of Branched Transportation

Related publications (14)

Programming Light Propagation for Efficient Artificial Intelligence

Contemporary artificial intelligence (AI) models' exponentially growing complexity translates to their expanding skill sets. They can create language or image content mimicking human creativity and understanding, becoming indispensable tools in education, ...

EPFL2025

Bayes-optimal learning of deep random networks of extensive-width*

Lenka Zdeborová, Florent Gérard Krzakala, Hugo Chao Cui

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

IOP Publishing Ltd2025

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

Michaël Unser, Sebastian Jonas Neumayer, Lénaïc Chizat

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

2024

Stochastic Homogenization of Functionals Defined on Finite Partitions

Matthias Benjamin Ruf

We prove a stochastic homogenization result for integral functionals defined on finite partitions assuming the surface tension to be stationary and possibly ergodic. We also consider the convergence of boundary value problems when we impose a boundary valu ...

Springer-Verlag Italia s.r.l.2024

LDP and CLT for SPDEs with transport noise

Lucio Galeati

In this work we consider solutions to stochastic partial differential equations with transport noise, which are known to converge, in a suitable scaling limit, to solution of the corresponding deterministic PDE with an additional viscosity term. Large devi ...

SPRINGER2023

We Need Subject Matter Expertise to Choose and Identify Causal Estimands: Comment on "Estimands for Recurrent Event Endpoints in the Presence of a Terminal Event"

Mats Julius Stensrud, Matias Janvin

We summarize what we consider to be the two main limitations of the "Estimands for Recurrent Event Endpoints in the Presence of a Terminal Event" (Schmidli et al. 2022). First, the authors did not give detailed guidance on how to choose an appropriate esti ...

TAYLOR & FRANCIS INC2023

Universal Approximation Property of Hamiltonian Deep Neural Networks

Giancarlo Ferrari Trecate, Muhammad Zakwan

This letter investigates the universal approximation capabilities of Hamiltonian Deep Neural Networks (HDNNs) that arise from the discretization of Hamiltonian Neural Ordinary Differential Equations. Recently, it has been shown that HDNNs enjoy, by design, ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Non-Linear Behaviors In The Dynamics Of Complex Systems Through A Multifractal Hydrodynamic Model

Maria-Alexandra Paun

Some non-linear behaviors in the dynamics of complex systems using the Scale Relativity Theory in the form of Multifractal Hydrodynamic Model are analyzed. By assimilating any complex system to a mathematical multifractal-type object, it is shown that the ...

UNIV POLITEHNICA BUCHAREST, SCI BULL2022

A large scale study of reader interactions with images on Wikipedia

Tiziano Piccardi

Wikipedia is the largest source of free encyclopedic knowledge and one of the most visited sites on the Web. To increase reader understanding of the article, Wikipedia editors add images within the text of the article's body. However, despite their widespr ...

SPRINGER2022

Uniformly perfect finitely generated simple left orderable groups

Yash Lodha

We show that the finitely generated simple left orderable groups G(rho) constructed by the first two authors in Hyde and Lodha [Finitely generated infinite simple groups of homeomorphisms of the real line. Invent. Math. (2019), doi:10.1007/s00222-01900880- ...

CAMBRIDGE UNIV PRESS2021

Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

Michaël Unser, Shayan Aziznejad, Harshit Gupta, Joaquim Gonçalves Garcia Barreto Campos

We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that end, ...

2020

Avoiding long Berge cycles: the missing casesk=r+1 andk=r+2

Abhishek Methuku

The maximum size of anr-uniform hypergraph without a Berge cycle of length at leastkhas been determined for allk >= r+ 3 by Furedi, Kostochka and Luo and fork

2020

Interactive visualization and analysis of morphological skeletons of brain vasculature networks with VessMorphoVis

Snigdha Dagar, Henry Markram, Felix Schürmann, Daniel Keller, Marwan Muhammad Ahmed Abdellah, Jean-Denis Georges Emile Courcol, Jay Coggan, Nadir Roman Guerrero, Benoît Jean-Albert Coste, Samuel Lieven D. Lapere

Motivation: Accurate morphological models of brain vasculature are key to modeling and simulating cerebral blood flow in realistic vascular networks. This in silico approach is fundamental to revealing the principles of neurovascular coupling. Validating t ...

Oxford University Press2020

Real-Time Optimization: Optimizing the Operation of Energy Systems in the Presence of Uncertainty and Disturbances

Dominique Bonvin, Grégory François

In practice, the quest for the optimal operation of energy systems is complicated by the simultaneous presence of operating constraints, among which the need for producing the power required by the user, and of uncertainty. The latter concept incorporates ...

2014