Toward a theory of pattern discovery
Conference Paper
This paper formalizes a latent variable inference problem we call 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.
Duke Authors
Cited Authors
- Huggins, J; Rudin, C
Published Date
- January 1, 2014
Published In
- International Symposium on Artificial Intelligence and Mathematics, Isaim 2014
Citation Source
- Scopus