papers

Publications (6)

cs.LG2023

Constrained Empirical Risk Minimization: Theory and Practice

Eric Marcus, Ray Sheombarsing, Jan-Jakob Sonke +1

Deep Neural Networks (DNNs) are widely used for their ability to effectively approximate large classes of functions. This flexibility, however, makes the strict enforcement of cons…

eess.IV2026

Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions

Ray Sheombarsing, Max van Riel, David Heesterbeek +2

Conventional MRI reconstruction methods treat images and coil sensitivities as discrete objects, leading to high memory demands and limited structural awareness that hamper effecti…

math.NA2024

Validated integration of semilinear parabolic PDEs

Jan Bouwe van den Berg, Maxime Breden, Ray Sheombarsing

Integrating evolutionary partial differential equations (PDEs) is an essential ingredient for studying the dynamics of the solutions. Indeed, simulations are at the core of scienti…

cs.CV2023

Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms

Joren Brunekreef, Eric Marcus, Ray Sheombarsing +2

Image segmentation algorithms can be understood as a collection of pixel classifiers, for which the outcomes of nearby pixels are correlated. Classifier models can be calibrated us…

math.DS2019

Validated computations for connecting orbits in polynomial vector fields

Jan Bouwe van den Berg, Ray Sheombarsing

In this paper we present a computer-assisted procedure for proving the existence of transverse heteroclinic orbits connecting hyperbolic equilibria of polynomial vector fields. The…

cs.CV2021

Subpixel object segmentation using wavelets and multi resolution analysis

Ray Sheombarsing, Nikita Moriakov, Jan-Jakob Sonke +1

We propose a novel deep learning framework for fast prediction of boundaries of two-dimensional simply connected domains using wavelets and Multi Resolution Analysis (MRA). The bou…