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
우리는 K. Yamanishi가 제안한 확장된 확률적 복잡성(ESC)을 분석합니다. ESC는 온라인 예측을 위한 학습 알고리즘과 일괄 학습 설정에 적용될 수 있습니다. Yanishi는 모든 데이터 시퀀스에 대해 균일하게 만족하는 ESC의 상한과 ESC의 점근적 기대의 상한을 도출했습니다. 그러나 Yamanishi는 주로 최악의 성능에 집중하고 있으며 하한값은 도출되지 않았습니다. 본 논문에서는 베이지안 통계와 유사한 ESC의 몇 가지 흥미로운 속성인 베이즈 규칙과 점근 정규성을 보여줍니다. 그런 다음 오류 내에서 거의 확실하고 평균적인 수렴을 의미하는 ESC의 점근 공식을 유도합니다. o(1) 이러한 속성을 사용합니다.
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
Masayuki GOTOH, Toshiyasu MATSUSHIMA, Shigeichi HIRASAWA, "Almost Sure and Mean Convergence of Extended Stochastic Complexity" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 10, pp. 2129-2137, October 1999, doi: .
Abstract: We analyze the extended stochastic complexity (ESC) which has been proposed by K. Yamanishi. The ESC can be applied to learning algorithms for on-line prediction and batch-learning settings. Yamanishi derived the upper bound of ESC satisfying uniformly for all data sequences and that of the asymptotic expectation of ESC. However, Yamanishi concentrates mainly on the worst case performance and the lower bound has not been derived. In this paper, we show some interesting properties of ESC which are similar to Bayesian statistics: the Bayes rule and the asymptotic normality. We then derive the asymptotic formula of ESC in the meaning of almost sure and mean convergence within an error of o(1) using these properties.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_10_2129/_p
부
@ARTICLE{e82-a_10_2129,
author={Masayuki GOTOH, Toshiyasu MATSUSHIMA, Shigeichi HIRASAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Almost Sure and Mean Convergence of Extended Stochastic Complexity},
year={1999},
volume={E82-A},
number={10},
pages={2129-2137},
abstract={We analyze the extended stochastic complexity (ESC) which has been proposed by K. Yamanishi. The ESC can be applied to learning algorithms for on-line prediction and batch-learning settings. Yamanishi derived the upper bound of ESC satisfying uniformly for all data sequences and that of the asymptotic expectation of ESC. However, Yamanishi concentrates mainly on the worst case performance and the lower bound has not been derived. In this paper, we show some interesting properties of ESC which are similar to Bayesian statistics: the Bayes rule and the asymptotic normality. We then derive the asymptotic formula of ESC in the meaning of almost sure and mean convergence within an error of o(1) using these properties.},
keywords={},
doi={},
ISSN={},
month={October},}
부
TY - JOUR
TI - Almost Sure and Mean Convergence of Extended Stochastic Complexity
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2129
EP - 2137
AU - Masayuki GOTOH
AU - Toshiyasu MATSUSHIMA
AU - Shigeichi HIRASAWA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1999
AB - We analyze the extended stochastic complexity (ESC) which has been proposed by K. Yamanishi. The ESC can be applied to learning algorithms for on-line prediction and batch-learning settings. Yamanishi derived the upper bound of ESC satisfying uniformly for all data sequences and that of the asymptotic expectation of ESC. However, Yamanishi concentrates mainly on the worst case performance and the lower bound has not been derived. In this paper, we show some interesting properties of ESC which are similar to Bayesian statistics: the Bayes rule and the asymptotic normality. We then derive the asymptotic formula of ESC in the meaning of almost sure and mean convergence within an error of o(1) using these properties.
ER -