Adaptive Online Prediction Using Weighted Windows

Shin-ichi YOSHIDA; Kohei HATANO; Eiji TAKIMOTO; Masayuki TAKEDA

doi:10.1587/transinf.E94.D.1917

Adaptive Online Prediction Using Weighted Windows

Shin-ichi YOSHIDA, Kohei HATANO, Eiji TAKIMOTO, Masayuki TAKEDA

Full Text Views

0

Share
Cite this

Summary :

We propose online prediction algorithms for data streams whose characteristics might change over time. Our algorithms are applications of online learning with experts. In particular, our algorithms combine base predictors over sliding windows with different length as experts. As a result, our algorithms are guaranteed to be competitive with the base predictor with the best fixed-length sliding window in hindsight.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.10 pp.1917-1923

Publication Date: 2011/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1917

Type of Manuscript: Special Section PAPER (Special Section on Information-Based Induction Sciences and Machine Learning)

Category

Cite this

Copy

Shin-ichi YOSHIDA, Kohei HATANO, Eiji TAKIMOTO, Masayuki TAKEDA, "Adaptive Online Prediction Using Weighted Windows" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 10, pp. 1917-1923, October 2011, doi: 10.1587/transinf.E94.D.1917.
Abstract: We propose online prediction algorithms for data streams whose characteristics might change over time. Our algorithms are applications of online learning with experts. In particular, our algorithms combine base predictors over sliding windows with different length as experts. As a result, our algorithms are guaranteed to be competitive with the base predictor with the best fixed-length sliding window in hindsight.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1917/_p

Copy

@ARTICLE{e94-d_10_1917,
author={Shin-ichi YOSHIDA, Kohei HATANO, Eiji TAKIMOTO, Masayuki TAKEDA, },
journal={IEICE TRANSACTIONS on Information},
title={Adaptive Online Prediction Using Weighted Windows},
year={2011},
volume={E94-D},
number={10},
pages={1917-1923},
abstract={We propose online prediction algorithms for data streams whose characteristics might change over time. Our algorithms are applications of online learning with experts. In particular, our algorithms combine base predictors over sliding windows with different length as experts. As a result, our algorithms are guaranteed to be competitive with the base predictor with the best fixed-length sliding window in hindsight.},
keywords={},
doi={10.1587/transinf.E94.D.1917},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Adaptive Online Prediction Using Weighted Windows
T2 - IEICE TRANSACTIONS on Information
SP - 1917
EP - 1923
AU - Shin-ichi YOSHIDA
AU - Kohei HATANO
AU - Eiji TAKIMOTO
AU - Masayuki TAKEDA
PY - 2011
DO - 10.1587/transinf.E94.D.1917
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2011
AB - We propose online prediction algorithms for data streams whose characteristics might change over time. Our algorithms are applications of online learning with experts. In particular, our algorithms combine base predictors over sliding windows with different length as experts. As a result, our algorithms are guaranteed to be competitive with the base predictor with the best fixed-length sliding window in hindsight.
ER -