Reducing statistical time-series problems to binary classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Reducing statistical time-series problems to binary classification

(1) , (1, 2)
1
2
Daniil Ryabko
  • Function : Author
  • PersonId : 848126

Abstract

We show how binary classification methods developed to work on i.i.d.\ data can be used for solving statistical problems that are seemingly unrelated to classification and concern highly-dependent time series. Specifically, the problems of time-series clustering, homogeneity testing and the three-sample problem are addressed. The algorithms that we construct for solving these problems are based on a new metric between time-series distributions, which can be evaluated using binary classification methods. Universal consistency of the proposed algorithms is proven under most general assumptions. The theoretical results are illustrated with experiments on synthetic and real-world data.
Fichier principal
Vignette du fichier
red_hal2.pdf (157.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00675637 , version 1 (01-03-2012)
hal-00675637 , version 2 (10-10-2012)
hal-00675637 , version 3 (21-10-2012)
hal-00675637 , version 4 (28-01-2013)
hal-00675637 , version 5 (07-06-2013)

Identifiers

  • HAL Id : hal-00675637 , version 5

Cite

Daniil Ryabko, Jérémie Mary. Reducing statistical time-series problems to binary classification. NIPS, Dec 2012, Lake Tahoe, United States. pp.2069--2077. ⟨hal-00675637v5⟩
233 View
231 Download

Share

Gmail Facebook Twitter LinkedIn More