Unified, provably consistent model-based clustering that jointly selects variables and handles MNAR via a data-driven penalty and explicit missingness–class modeling, validated on transcriptomics.

We establish non-asymptotic minimax separation rates for univariate function selection in sparse additive models, and discuss the difference between optimal estimation and selection.

We propose two scalable DP algorithms for high-dimensional sparse variable selection, leveraging modern mixed-integer programming techniques.