We consider post-selection inference for high-dimensional (generalized) linear models. Data carving from Fithian, Sun and Taylor [10] is a promising technique to perform this task. However, it suffers the instability of model selector hence, may lead poor replicability, especially in settings. propose multicarve method inspired by multisplitting improve upon stability replicability. Furthermore...

Most of the work we do in signal processing these days is data driven. The shift from more traditional and model-driven approaches to those that are driven has also underlined importance explainability our solutions. Because most start with a number modeling assumptions, they comprehensible by very nature their construction. However, this not necessarily case when choose rely heavily on minimiz...