Paperlane

no. 13 · Wednesday 11 November 2026

Smoothed Least-Absolute Conditional Multidimensional Scaling via Iteratively Reweighted Majorization

Xiao Ling

math.ST · 33 pp

Abstract

Conditional multidimensional scaling combines latent coordinates with observed covariates to fit pairwise dissimilarities. We develop a smoothed l1 formulation using the shifted Charbonnier loss. We prove residualwise sharpness of the quadratic loss majorizer, monotonicity, compact containment, and stationarity of noncollapsed accumulation points. A uniform additive bound quantifies approximation to exact least-absolute conditional stress. The experiments use paired contamination, separately calibrated loss parameters, combined-configuration recovery, and direct checks of the theorem's inequalities.

comments
33 pages, 6 figures, 8 tables
fields
Statistics Theory, Optimization and Control
pdf ↗ page arXiv:2611.14345 ↗