• <ins id="pjuwb"></ins>
    <blockquote id="pjuwb"><pre id="pjuwb"></pre></blockquote>
    <noscript id="pjuwb"></noscript>
          <sup id="pjuwb"><pre id="pjuwb"></pre></sup>
            <dd id="pjuwb"></dd>
            <abbr id="pjuwb"></abbr>

            O(1) 的小樂

            Job Hunting

            公告

            記錄我的生活和工作。。。
            <2010年10月>
            262728293012
            3456789
            10111213141516
            17181920212223
            24252627282930
            31123456

            統(tǒng)計

            • 隨筆 - 182
            • 文章 - 1
            • 評論 - 41
            • 引用 - 0

            留言簿(10)

            隨筆分類(70)

            隨筆檔案(182)

            文章檔案(1)

            如影隨形

            搜索

            •  

            最新隨筆

            最新評論

            閱讀排行榜

            評論排行榜

            Kullback–Leibler divergence KL散度

            In probability theory and information theory, the Kullback–Leibler divergence[1][2][3] (also information divergence,information gain, relative entropy, or KLIC) is a non-symmetric measure of the difference between two probability distributions P and Q. KL measures the expected number of extra bits required to code samples from P when using a code based on Q, rather than using a code based on P. Typically P represents the "true" distribution of data, observations, or a precise calculated theoretical distribution. The measure Q typically represents a theory, model, description, or approximation of P.

            Although it is often intuited as a distance metric, the KL divergence is not a true metric – for example, the KL from P to Q is not necessarily the same as the KL from Q to P.

            KL divergence is a special case of a broader class of divergences called f-divergences. Originally introduced by Solomon Kullbackand Richard Leibler in 1951 as the directed divergence between two distributions, it is not the same as a divergence incalculus. However, the KL divergence can be derived from the Bregman divergence.

             

             

            注意P通常指數(shù)據(jù)集,我們已有的數(shù)據(jù)集,Q表示理論結(jié)果,所以KL divergence 的物理含義就是當(dāng)用Q來編碼P中的采樣時,比用P來編碼P中的采用需要多用的位數(shù)!

             

            KL散度,也有人稱為KL距離,但是它并不是嚴(yán)格的距離概念,其不滿足三角不等式

             

            KL散度是不對稱的,當(dāng)然,如果希望把它變對稱,

            Ds(p1, p2) = [D(p1, p2) + D(p2, p1)] / 2

             

            下面是KL散度的離散和連續(xù)定義!

            D_{\mathrm{KL}}(P\|Q) = \sum_i P(i) \log \frac{P(i)}{Q(i)}. \!

            D_{\mathrm{KL}}(P\|Q) = \int_{-\infty}^\infty p(x) \log \frac{p(x)}{q(x)} \; dx, \!

            注意的一點是p(x) 和q(x)分別是pq兩個隨機變量的PDF,D(P||Q)是一個數(shù)值,而不是一個函數(shù),看下圖!

             

            注意:KL Area to be Integrated!

             

            File:KL-Gauss-Example.png

             

            KL 散度一個很強大的性質(zhì):

            The Kullback–Leibler divergence is always non-negative,

            D_{\mathrm{KL}}(P\|Q) \geq 0, \,

            a result known as , with DKL(P||Q) zero if and only if P = Q.

             

            計算KL散度的時候,注意問題是在稀疏數(shù)據(jù)集上KL散度計算通常會出現(xiàn)分母為零的情況!

             

             

            Matlab中的函數(shù):KLDIV給出了兩個分布的KL散度

            Description

            KLDIV Kullback-Leibler or Jensen-Shannon divergence between two distributions.

            KLDIV(X,P1,P2) returns the Kullback-Leibler divergence between two distributions specified over the M variable values in vector X. P1 is a length-M vector of probabilities representing distribution 1, and P2 is a length-M vector of probabilities representing distribution 2. Thus, the probability of value X(i) is P1(i) for distribution 1 and P2(i) for distribution 2. The Kullback-Leibler divergence is given by:

               KL(P1(x),P2(x)) = sum[P1(x).log(P1(x)/P2(x))]

            If X contains duplicate values, there will be an warning message, and these values will be treated as distinct values. (I.e., the actual values do not enter into the computation, but the probabilities for the two duplicate values will be considered as probabilities corresponding to two unique values.) The elements of probability vectors P1 and P2 must each sum to 1 +/- .00001.

            A "log of zero" warning will be thrown for zero-valued probabilities. Handle this however you wish. Adding 'eps' or some other small value to all probabilities seems reasonable. (Renormalize if necessary.)

            KLDIV(X,P1,P2,'sym') returns a symmetric variant of the Kullback-Leibler divergence, given by [KL(P1,P2)+KL(P2,P1)]/2. See Johnson and Sinanovic (2001).

            KLDIV(X,P1,P2,'js') returns the Jensen-Shannon divergence, given by [KL(P1,Q)+KL(P2,Q)]/2, where Q = (P1+P2)/2. See the Wikipedia article for "Kullback–Leibler divergence". This is equal to 1/2 the so-called "Jeffrey divergence." See Rubner et al. (2000).

            EXAMPLE: Let the event set and probability sets be as follow:
               X = [1 2 3 3 4]';
               P1 = ones(5,1)/5;
               P2 = [0 0 .5 .2 .3]' + eps;
            Note that the event set here has duplicate values (two 3's). These will be treated as DISTINCT events by KLDIV. If you want these to be treated as the SAME event, you will need to collapse their probabilities together before running KLDIV. One way to do this is to use UNIQUE to find the set of unique events, and then iterate over that set, summing probabilities for each instance of each unique event. Here, we just leave the duplicate values to be treated independently (the default):
               KL = kldiv(X,P1,P2);
               KL =
                    19.4899

            Note also that we avoided the log-of-zero warning by adding 'eps' to all probability values in P2. We didn't need to renormalize because we're still within the sum-to-one tolerance.

            REFERENCES:
            1) Cover, T.M. and J.A. Thomas. "Elements of Information Theory," Wiley, 1991.
            2) Johnson, D.H. and S. Sinanovic. "Symmetrizing the Kullback-Leibler distance." IEEE Transactions on Information Theory (Submitted).
            3) Rubner, Y., Tomasi, C., and Guibas, L. J., 2000. "The Earth Mover's distance as a metric for image retrieval." International Journal of Computer Vision, 40(2): 99-121.
            4) <a href="
            http://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence"&gt;Kullback–Leibler divergence</a>. Wikipedia, The Free Encyclopedia.

            posted on 2010-10-16 15:04 Sosi 閱讀(10020) 評論(2)  編輯 收藏 引用 所屬分類: Taps in Research

            評論

            # re: Kullback&ndash;Leibler divergence KL散度 2010-11-30 16:17 tintin0324

            博主,本人的研究方向需要了解kl距離,有些問題想請教下,怎么聯(lián)系呢?
              回復(fù)  更多評論    

            # re: Kullback&ndash;Leibler divergence KL散度 2010-12-05 22:37 Sosi

            @tintin0324
            KL 距離本身很簡單,如果就是那樣子定義的,意義也如上面所說。。如果你想深入了解的話,可以讀以下相關(guān)文獻(xiàn)
              回復(fù)  更多評論    
            統(tǒng)計系統(tǒng)
            精品久久久无码人妻中文字幕| 欧美激情精品久久久久久久| 久久人妻AV中文字幕| 亚洲天堂久久久| 91精品国产91久久久久久蜜臀| 久久久久亚洲精品无码网址| 思思久久99热只有频精品66| 久久国产乱子伦免费精品| 久久av高潮av无码av喷吹| 国产精品久久久久国产A级| 女人高潮久久久叫人喷水| 99久久国语露脸精品国产| 久久精品无码午夜福利理论片 | 1000部精品久久久久久久久| 国产福利电影一区二区三区久久久久成人精品综合 | 精品久久久久久久久中文字幕| 伊人久久大香线蕉综合Av| 中文字幕无码久久精品青草 | 久久久网中文字幕| 久久精品国产亚洲沈樵| 狠狠精品久久久无码中文字幕| 国产精品熟女福利久久AV| 久久久久人妻精品一区 | 久久亚洲欧美日本精品| 国产精品青草久久久久婷婷| 国产精品一区二区久久精品涩爱 | 66精品综合久久久久久久| 久久精品一本到99热免费| 久久午夜夜伦鲁鲁片免费无码影视| 国产激情久久久久影院老熟女免费| 精品久久久久中文字幕日本| 新狼窝色AV性久久久久久| 久久久久久久久无码精品亚洲日韩| 久久无码人妻精品一区二区三区| 久久91精品国产91久久小草| 色综合久久久久无码专区| 久久人人爽人人爽人人片AV东京热| 欧美精品福利视频一区二区三区久久久精品 | 综合人妻久久一区二区精品| 亚洲精品NV久久久久久久久久| 久久婷婷五月综合色99啪ak|