Defensive forecasting for optimal prediction with expert advice. / Vovk, Vladimir.

2007.

Research output: Working paper

Published

Standard

Harvard

APA

Vancouver

Author

BibTeX

@techreport{a3b4316dac7f46d78998d7414105a373,
title = "Defensive forecasting for optimal prediction with expert advice",
abstract = "The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of {"}second-guessing{"} experts, whose advice depends on the learner's prediction; this paper assumes that the dependence on the learner's prediction is continuous.",
keywords = "cs.LG",
author = "Vladimir Vovk",
note = "14 pages",
year = "2007",
month = aug,
day = "10",
language = "English",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Defensive forecasting for optimal prediction with expert advice

AU - Vovk, Vladimir

N1 - 14 pages

PY - 2007/8/10

Y1 - 2007/8/10

N2 - The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of "second-guessing" experts, whose advice depends on the learner's prediction; this paper assumes that the dependence on the learner's prediction is continuous.

AB - The method of defensive forecasting is applied to the problem of prediction with expert advice for binary outcomes. It turns out that defensive forecasting is not only competitive with the Aggregating Algorithm but also handles the case of "second-guessing" experts, whose advice depends on the learner's prediction; this paper assumes that the dependence on the learner's prediction is continuous.

KW - cs.LG

M3 - Working paper

BT - Defensive forecasting for optimal prediction with expert advice

ER -