翻訳と辞書 Words near each other ・ Minimum Wages Act 1948 ・ Minimum weight ・ Minimum-cost flow problem ・ Minimum-Maximum ・ Minimum-Maximum (video) ・ Minimum-shift keying ・ Minimum-variance unbiased estimator ・ Minimum-weight triangulation ・ Minimumweight ・ Minimundus ・ Minimus ・ Minimusical ・ Minin ・ Minimax Condorcet ・ MiniMAX Discount ・ Minimax estimator ・ Minimax eversion ・ Minimax Limited ・ Minimay, Victoria ・ Minimaze procedure ・ Minimbah railway station ・ Minime ・ Minimed Paradigm ・ Minimello ・ Minimerg ・ Minimetrò ・ Minimi ・ Minimidget ・ Minimig ・ MiniMini+ Dictionary Lists mini英和辞書 mini和英辞書 Webster 1913 Latin-English FOLDOC Wikipedia English ウィキペディア

翻訳と辞書　辞書検索 [ 開発暫定版 ] スポンサード リンク Minimax estimator ： ウィキペディア英語版 Minimax estimator In statistical decision theory, where we are faced with the problem of estimating a deterministic parameter (vector) $\backslash theta\; \backslash in\; \backslash Theta$ from observations $x\; \backslash in\; \backslash mathcal,$ an estimator (estimation rule) $\backslash delta^M\; \backslash ,\backslash !$ is called minimax if its maximal risk is minimal among all estimators of $\backslash theta\; \backslash ,\backslash !$. In a sense this means that $\backslash delta^M\; \backslash ,\backslash !$ is an estimator which performs best in the worst possible case allowed in the problem. ==Problem setup== Consider the problem of estimating a deterministic (not Bayesian) parameter $\backslash theta\; \backslash in\; \backslash Theta$ from noisy or corrupt data $x\; \backslash in\; \backslash mathcal$ related through the conditional probability distribution $P(x|\backslash theta)\backslash ,\backslash !$. Our goal is to find a "good" estimator $\backslash delta(x)\; \backslash ,\backslash !$ for estimating the parameter $\backslash theta\; \backslash ,\backslash !$, which minimizes some given risk function $R(\backslash theta,\backslash delta)\; \backslash ,\backslash !$. Here the risk function is the expectation of some loss function $L(\backslash theta,\backslash delta)\; \backslash ,\backslash !$ with respect to $P(x|\backslash theta)\backslash ,\backslash !$. A popular example for a loss function is the squared error loss $L(\backslash theta,\backslash delta)=\; \backslash |\backslash theta-\backslash delta\backslash |^2\; \backslash ,\backslash !$, and the risk function for this loss is the mean squared error (MSE). Unfortunately in general the risk cannot be minimized, since it depends on the unknown parameter $\backslash theta\; \backslash ,\backslash !$ itself (If we knew what was the actual value of $\backslash theta\; \backslash ,\backslash !$, we wouldn't need to estimate it). Therefore additional criteria for finding an optimal estimator in some sense are required. One such criterion is the minimax criteria. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Minimax estimator」の詳細全文を読む スポンサード リンク 翻訳と辞書 : 翻訳のためのインターネットリソース Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.