The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
머신러닝에서 가장 중요한 문제 중 하나는 알려지지 않은 소스에서 생성된 현재 단계까지의 일련의 결과를 관찰하여 이진 값을 예측하는 것입니다. Vovk 및 Cesa-Bianchi et al. 예측 알고리즘에 전문가라고 불리는 예측 전략 모음이 주어지고 따라서 그들이 만드는 예측을 사용할 수 있다고 가정하는 온라인 예측 모델을 독립적으로 제안했습니다. 이 모델에서는 예측할 비트 시퀀스가 생성되는 방식에 대해 어떠한 가정도 하지 않으며, 알고리즘의 성능은 비트 시퀀스에서 발생한 실수 수와 해당 비트 시퀀스에서 발생한 실수 수의 차이로 측정됩니다. 동일한 시퀀스에 대한 최고의 전문가. 본 논문에서는 투자 개념을 도입하여 모델을 확장합니다. 즉, 예측 알고리즘과 전문가 모두 각 시간 단계에서 자신의 예측에 대해 배팅을 해야 하며, 이제 알고리즘의 성능은 실수 횟수가 아닌 총 손실 금액을 기준으로 측정됩니다. 우리는 모든 전문가가 각 단계에서 동일한 양의 베팅을 공유하는 특정 상황에서 알고리즘을 분석합니다. 이 공유 베팅 모델에서 우리는 어떤 의미에서는 최적이지만 비현실적인 예측 알고리즘을 제공하고 거의 최적인 것으로 판명되는 효율적인 예측 알고리즘도 제공합니다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Ichiro TAJIKA, Eiji TAKIMOTO, Akira MARUOKA, "An On-Line Prediction Algorithm Combining Several Prediction Strategies in the Shared Bet Model" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 2, pp. 348-355, February 1999, doi: .
Abstract: One of the most important problems in machine learning is to predict a binary value by observing a sequence of outcomes, up to the present time step, generated from some unknown source. Vovk and Cesa-Bianchi et al. independently proposed an on-line prediction model where prediction algorithms are assumed to be given a collection of prediction strategies called experts and hence be allowed to use the predictions they make. In this model, no assumption is made about the way the sequence of bits to be predicted is generated, and the performance of the algorithm is measured by the difference between the number of mistakes it makes on the bit sequence and the number of mistakes made by the best expert on the same sequence. In this paper we extend the model by introducing a notion of investment. That is, both the prediction algorithm and the experts are required to make bets on their predictions at each time step, and the performance of the algorithm is now measured with respect to the total money lost, rather than the number of mistakes. We analyze our algorithms in the particular situation where all the experts share the same amount of bets at each time step. In this shared bet model, we give a prediction algorithm that is in some sense optimal but impractical, and we also give an efficient prediction algorithm that turns out to be nearly optimal.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_2_348/_p
부
@ARTICLE{e82-d_2_348,
author={Ichiro TAJIKA, Eiji TAKIMOTO, Akira MARUOKA, },
journal={IEICE TRANSACTIONS on Information},
title={An On-Line Prediction Algorithm Combining Several Prediction Strategies in the Shared Bet Model},
year={1999},
volume={E82-D},
number={2},
pages={348-355},
abstract={One of the most important problems in machine learning is to predict a binary value by observing a sequence of outcomes, up to the present time step, generated from some unknown source. Vovk and Cesa-Bianchi et al. independently proposed an on-line prediction model where prediction algorithms are assumed to be given a collection of prediction strategies called experts and hence be allowed to use the predictions they make. In this model, no assumption is made about the way the sequence of bits to be predicted is generated, and the performance of the algorithm is measured by the difference between the number of mistakes it makes on the bit sequence and the number of mistakes made by the best expert on the same sequence. In this paper we extend the model by introducing a notion of investment. That is, both the prediction algorithm and the experts are required to make bets on their predictions at each time step, and the performance of the algorithm is now measured with respect to the total money lost, rather than the number of mistakes. We analyze our algorithms in the particular situation where all the experts share the same amount of bets at each time step. In this shared bet model, we give a prediction algorithm that is in some sense optimal but impractical, and we also give an efficient prediction algorithm that turns out to be nearly optimal.},
keywords={},
doi={},
ISSN={},
month={February},}
부
TY - JOUR
TI - An On-Line Prediction Algorithm Combining Several Prediction Strategies in the Shared Bet Model
T2 - IEICE TRANSACTIONS on Information
SP - 348
EP - 355
AU - Ichiro TAJIKA
AU - Eiji TAKIMOTO
AU - Akira MARUOKA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1999
AB - One of the most important problems in machine learning is to predict a binary value by observing a sequence of outcomes, up to the present time step, generated from some unknown source. Vovk and Cesa-Bianchi et al. independently proposed an on-line prediction model where prediction algorithms are assumed to be given a collection of prediction strategies called experts and hence be allowed to use the predictions they make. In this model, no assumption is made about the way the sequence of bits to be predicted is generated, and the performance of the algorithm is measured by the difference between the number of mistakes it makes on the bit sequence and the number of mistakes made by the best expert on the same sequence. In this paper we extend the model by introducing a notion of investment. That is, both the prediction algorithm and the experts are required to make bets on their predictions at each time step, and the performance of the algorithm is now measured with respect to the total money lost, rather than the number of mistakes. We analyze our algorithms in the particular situation where all the experts share the same amount of bets at each time step. In this shared bet model, we give a prediction algorithm that is in some sense optimal but impractical, and we also give an efficient prediction algorithm that turns out to be nearly optimal.
ER -