[2603.26327] Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?

Statistics > Methodology arXiv:2603.26327 (stat) [Submitted on 27 Mar 2026] Title:Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why? Authors:Bailey Andrew, David R. Westhead, Luisa Cutillo View a PDF of the paper titled Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?, by Bailey Andrew and 2 other authors View PDF HTML (experimental) Abstract:In this paper we develop a graph-learning algorithm, MED-MAGMA, to fit multi-axis (Kronecker-sum-structured) models corrupted by multiplicative noise. This type of noise is natural in many application domains, such as that of single-cell RNA sequencing, in which it naturally captures technical biases of RNA sequencing platforms. Our work is evaluated against prior work on each and every public dataset in the Single Cell Expression Atlas under a certain size, demonstrating that our methodology learns networks with better local and global structure. MED-MAGMA is made available as a Python package (MED-MAGMA). Comments: Subjects: Methodology (stat.ME); Machine Learning (cs.LG) Cite as: arXiv:2603.26327 [stat.ME]   (or arXiv:2603.26327v1 [stat.ME] for this version)   https://doi.org/10.48550/arXiv.2603.26327 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Bailey Andrew [view email] [v1] Fri, 27 Mar 2026 11:44:52 UTC (117 KB) Full-text links: Access Paper: View a PDF of the paper titled Making Multi-Axis Models Robust to Multiplicative Noise: How, a...