Time-series information and learning

Ryabko, Daniil

Document type :

Communication dans un congrès avec actes

Title :

Time-series information and learning

Author(s) :

Ryabko, Daniil [Auteur]
Sequential Learning [SEQUEL]

Conference title :

ISIT - International Symposium on Information Theory

City :

Istanbul

Country :

Turquie

Start date of the conference :

2013

Publication date :

2013

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

Given a time series $X_1,\dots,X_n,\dots$ taking values in a large (high-dimensional) space $\cX$, we would like to find a function $f$ from $\cX$ to a small (low-dimensional or finite) space $\cY$ such that the time series ...
Show more >Given a time series $X_1,\dots,X_n,\dots$ taking values in a large (high-dimensional) space $\cX$, we would like to find a function $f$ from $\cX$ to a small (low-dimensional or finite) space $\cY$ such that the time series $f(X_1),\dots,f(X_n),\dots$ retains all the information about the time-series dependence in the original sequence, or as much as possible thereof. This goal is formalized in this work, and it is shown that the target function $f$ can be found as the one that maximizes a certain quantity that can be expressed in terms of entropies of the series $(f(X_i))_{i\in\N}$. This quantity can be estimated empirically, and does not involve estimating the distribution on the original time series $(X_i)_{i\in\N}$.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Time-series information and learning BibTeX CSV Excel RIS

Time-series information and learning

BibTeX

CSV

Excel

RIS