Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible

Daniil Ryabko; Boris Ryabko

doi:10.1109/ISIT.2015.7282646

Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › рецензирование

2 Цитирования (Scopus)

Аннотация

The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.

Язык оригинала	английский
Название основной публикации	Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015
Издатель	Institute of Electrical and Electronics Engineers Inc.
Страницы	1204-1206
Число страниц	3
ISBN (электронное издание)	9781467377041
DOI	https://doi.org/10.1109/ISIT.2015.7282646
Состояние	Опубликовано - 28 сен 2015
Опубликовано для внешнего пользования	Да
Событие	IEEE International Symposium on Information Theory, ISIT 2015 - Hong Kong, Гонконг Продолжительность: 14 июн 2015 → 19 июн 2015

Серия публикаций

Название	IEEE International Symposium on Information Theory - Proceedings
Том	2015-June
ISSN (печатное издание)	2157-8095

Конференция

Конференция	IEEE International Symposium on Information Theory, ISIT 2015
Страна	Гонконг
Город	Hong Kong
Период	14.06.2015 → 19.06.2015

Доступ к документу

10.1109/ISIT.2015.7282646

Link to publication in Scopus

Fingerprint Подробные сведения о темах исследования «Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать

Ryabko, D., & Ryabko, B. (2015). Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. В Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015 (стр. 1204-1206). [7282646] (IEEE International Symposium on Information Theory - Proceedings; Том 2015-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT.2015.7282646

Ryabko, Daniil ; Ryabko, Boris. / Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015. Institute of Electrical and Electronics Engineers Inc., 2015. стр. 1204-1206 (IEEE International Symposium on Information Theory - Proceedings).

@inproceedings{e9fdabe4a68d47979de7980141f11101,

title = "Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible",

abstract = "The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.",

author = "Daniil Ryabko and Boris Ryabko",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/ISIT.2015.7282646",

language = "English",

series = "IEEE International Symposium on Information Theory - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1204--1206",

booktitle = "Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015",

address = "United States",

note = "IEEE International Symposium on Information Theory, ISIT 2015 ; Conference date: 14-06-2015 Through 19-06-2015",

}

Ryabko, D & Ryabko, B 2015, Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. в Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015., 7282646, IEEE International Symposium on Information Theory - Proceedings, том. 2015-June, Institute of Electrical and Electronics Engineers Inc., стр. 1204-1206, IEEE International Symposium on Information Theory, ISIT 2015, Hong Kong, Гонконг, 14.06.2015. https://doi.org/10.1109/ISIT.2015.7282646

Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. / Ryabko, Daniil; Ryabko, Boris.

Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015. Institute of Electrical and Electronics Engineers Inc., 2015. стр. 1204-1206 7282646 (IEEE International Symposium on Information Theory - Proceedings; Том 2015-June).

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › рецензирование

TY - GEN

T1 - Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible

AU - Ryabko, Daniil

AU - Ryabko, Boris

PY - 2015/9/28

Y1 - 2015/9/28

N2 - The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.

AB - The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.

UR - http://www.scopus.com/inward/record.url?scp=84969786555&partnerID=8YFLogxK

U2 - 10.1109/ISIT.2015.7282646

DO - 10.1109/ISIT.2015.7282646

M3 - Conference contribution

AN - SCOPUS:84969786555

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 1204

EP - 1206

BT - Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Symposium on Information Theory, ISIT 2015

Y2 - 14 June 2015 through 19 June 2015

ER -

Ryabko D, Ryabko B. Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. В Proceedings - 2015 IEEE International Symposium on Information Theory, ISIT 2015. Institute of Electrical and Electronics Engineers Inc. 2015. стр. 1204-1206. 7282646. (IEEE International Symposium on Information Theory - Proceedings). https://doi.org/10.1109/ISIT.2015.7282646