Obtaining Partition Crossover masks using Statistical Linkage Learning for solving noised optimization problems with hidden variable dependency structure

ArXiv stat_ml new submissions (2026-04-15) containing 10 papers across optimization, theory, robustness, and causal/probabilistic modeling. Key contributions include: an SLL-based mask construction that recovers Partition Crossover masks and enables noise-robust optimization; a continuum variational limit and well-posedness analysis for t-SNE; a Cumulative Standardized Binomial EWMA (CSB-EWMA) with exact time-varying variance for multi-stream binary SPC; a transfer-learning fine-tuning method (FAN-Lasso) for high-dimensional nonparametric regression with variable selection; an information-geom