Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification
Journal of Mathematical Imaging and Vision · 2026-10 · 68 (5)
DOI: 10.1007/s10851-026-01345-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mathematical Imaging and Vision, online erschienen am 22.08.2026. Verfasst von Jack Michael Solomon und 2 weiteren Autor:innen. Die Arbeit nennt 71 Literaturangaben.
Abstract (Originalsprache)
Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements. Many applications demand not just point estimates but interpretable uncertainty. Providing fast inference alongside uncertainty estimates remains challenging yet desirable in numerous applications. We propose the Variational Sparse Paired Autoencoder (vsPAIR) to address this challenge. The architecture pairs a standard VAE encoding observations with a sparse VAE encoding quantities of interest (QoI), connected through a learned latent mapping. The variational structure enables uncertainty aware estimation, the paired architecture encourages interpretability by anchoring QoI representations to clean data, and sparse encodings provide structure by concentrating information into identifiable factors rather than diffusing across all dimensions. To validate the effectiveness of our proposed architecture, we conduct experiments on blind inpainting, computed tomography (CT), and initial-condition inference for the heat equation, demonstrating that vsPAIR is a capable inverse problem solver that can provide interpretable and structured uncertainty estimates.
Zitieren
APA
Solomon, J. M., Leburu, R., & Chung, M. (2026). Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification. Journal of Mathematical Imaging and Vision, 68(5). https://doi.org/10.1007/s10851-026-01345-2
Vancouver
Solomon JM, Leburu R, Chung M. Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification. Journal of Mathematical Imaging and Vision. 2026;68(5). doi:10.1007/s10851-026-01345-2
BibTeX
@article{Solomon2026,
author = {Solomon, Jack Michael and Leburu, Rishi and Chung, Matthias},
title = {Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification},
journal = {Journal of Mathematical Imaging and Vision},
year = {2026},
volume = {68},
number = {5},
doi = {10.1007/s10851-026-01345-2}
}
EUVIMED