A Statistical Learning Theory Framework for Supervised Pattern Discovery
It addresses a theoretical gap in statistical learning for pattern discovery, but is incremental as it builds on existing frameworks.
The paper formalizes supervised pattern discovery as a latent variable inference problem and proves uniform risk bounds for two versions: one with arbitrarily generated pattern collections and another with independently generated patterns, introducing quasi-Rademacher complexity as a new measure.
This paper formalizes a latent variable inference problem we call {\em supervised pattern discovery}, the goal of which is to find sets of observations that belong to a single ``pattern.'' We discuss two versions of the problem and prove uniform risk bounds for both. In the first version, collections of patterns can be generated in an arbitrary manner and the data consist of multiple labeled collections. In the second version, the patterns are assumed to be generated independently by identically distributed processes. These processes are allowed to take an arbitrary form, so observations within a pattern are not in general independent of each other. The bounds for the second version of the problem are stated in terms of a new complexity measure, the quasi-Rademacher complexity.