An impossibility result for process discrimination

Daniil Ryabko 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : Two series of binary observations $x_1,x_1,\dots$ and $y_1,y_2,\dots$ are presented: at each time $n\in\N$ we are given $x_n$ and $y_n$. It is assumed that the sequences are generated independently of each other by two B-processes. We are interested in the question of whether the sequences represent a typical realization of two different processes or of the same one. We demonstrate that this is impossible to decide, in the sense that every discrimination procedure is bound to err with non-negligible frequency when presented with sequences from some B-processes. This contrasts earlier positive results on B-processes, in particular those showing that there are consistent $\bar d$-distance estimates for this class of processes.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/inria-00319076
Contributor : Daniil Ryabko <>
Submitted on : Friday, July 10, 2009 - 11:30:56 AM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Friday, September 24, 2010 - 2:39:50 PM

Files

discr.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00319076, version 7
  • ARXIV : 0809.1053

Collections

Citation

Daniil Ryabko. An impossibility result for process discrimination. International Symposium on Information Theory, IEEE, 2009, Seoul, South Korea. pp.1734-1738. ⟨inria-00319076v7⟩

Share

Metrics

Record views

280

Files downloads

271