Chapter

Learning Theory

Volume 3120 of the series Lecture Notes in Computer Science pp 186-199

Inferring Mixtures of Markov Chains

  • Tuğkan BatuAffiliated withCarnegie Mellon UniversityDepartment of Computer Sciences, University of Texas
  • , Sudipto GuhaAffiliated withCarnegie Mellon UniversityDepartment of Computer and Information Science, University of Pennsylvania
  • , Sampath KannanAffiliated withCarnegie Mellon UniversityDepartment of Computer and Information Science, University of Pennsylvania

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We define the problem of inferring a “mixture of Markov chains” based on observing a stream of interleaved outputs from these chains. We show a sharp characterization of the inference process. The problems we consider also has applications such as gene finding, intrusion detection, etc., and more generally in analyzing interleaved sequences.