activity
20242026
collaborators

5 papers

cs.LG2026

Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes

Maria Bånkestad, Sanna Jarl, Jens Sjölund

Gaussian processes with stationary kernels on bounded domains exhibit inflated posterior variance near the boundary. Despite being a long-recognized artifact in geostatistics and a…

physics.comp-ph2026

A differentiable machine learning small-angle X-ray scattering analysis framework for structure elucidation of lipid nanoparticles

Maria Bånkestad, Sandra Barman, Magnus Röding +11

Lipid nanoparticles (LNPs) are efficient delivery systems for negatively charged nucleic acids. Their multi-component architecture yields a core-shell structure. Small-angle X-ray…

cs.LG2026

Observation-dependent Bayesian active learning via input-warped Gaussian processes

Sanna Jarl, Maria BÃ¥nkestad, Jonathan J. S. Scragg +1

Bayesian active learning relies on the precise quantification of predictive uncertainty to explore unknown function landscapes. While Gaussian process surrogates are the standard f…

cs.LG2025

Ising on the Graph: Task-specific Graph Subsampling via the Ising Model

Maria BÃ¥nkestad, Jennifer R. Andersson, Sebastian Mair +1

Reducing a graph while preserving its overall properties is an important problem with many applications. Typically, reduction approaches either remove edges (sparsification) or mer…

cs.LG2024

Flexible SE(2) graph neural networks with applications to PDE surrogates

Maria BÃ¥nkestad, Olof Mogren, Aleksis Pirinen

This paper presents a novel approach for constructing graph neural networks equivariant to 2D rotations and translations and leveraging them as PDE surrogates on non-gridded domain…