uniform Effect of K-means Clustering











up vote
0
down vote

favorite












In the following link is discussed the uniform Effect of K-means Clustering:



https://www.springer.com/cda/content/document/cda_downloaddocument/9783642298066-c2.pdf?SGWID=0-0-45-1338325-p174318763



He used the following equation:




$ frac{displaystyle2 d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




where




$ d(C_1,C_2)=sum_{x_iin C_1}sum_{x_jin C_2}||x_i−x_j||^2$ with $ |C_1|=n_1$ and $|C_2 |=n_2$.




I tried to prove this, but I do not get this. He uses the fact that




$ d(C_1,C_1)=2(n_1-1)sum_{i=1}^{n_1} ||x_i||^2 -4 sum_{1leq i < j leq n_1}langle x_i,x_jrangle.$



$ d(C_2,C_2)=2(n_2-1)sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq i < j leq n_2}langle y_i,y_jrangle.$



$ d(C_1,C_2)=2n_2sum_{i=1}^{n_1} ||x_i||^2+2n_1sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle.$




And furthermore with




$||m_1−m_2||^2=langle sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2,sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2 rangle = frac{1}{displaystyle n_1^2}sum_{i=1}^{n_1} ||x_i||^2 + frac{2}{displaystyle n_1^2}sum_{1leq i < jleq n_1} langle x_i, x_jrangle +frac{1}{displaystyle n_2^2}sum_{i=1}^{n_2} ||y_i||^2 + frac{2}{displaystyle n_2^2}sum_{1leq i < jleq n_2} langle y_i, y_jrangle - frac{2}{n_1n_2} sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle, $




I obtain that




$ frac{displaystyle d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




Where is my error?










share|cite|improve this question




























    up vote
    0
    down vote

    favorite












    In the following link is discussed the uniform Effect of K-means Clustering:



    https://www.springer.com/cda/content/document/cda_downloaddocument/9783642298066-c2.pdf?SGWID=0-0-45-1338325-p174318763



    He used the following equation:




    $ frac{displaystyle2 d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




    where




    $ d(C_1,C_2)=sum_{x_iin C_1}sum_{x_jin C_2}||x_i−x_j||^2$ with $ |C_1|=n_1$ and $|C_2 |=n_2$.




    I tried to prove this, but I do not get this. He uses the fact that




    $ d(C_1,C_1)=2(n_1-1)sum_{i=1}^{n_1} ||x_i||^2 -4 sum_{1leq i < j leq n_1}langle x_i,x_jrangle.$



    $ d(C_2,C_2)=2(n_2-1)sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq i < j leq n_2}langle y_i,y_jrangle.$



    $ d(C_1,C_2)=2n_2sum_{i=1}^{n_1} ||x_i||^2+2n_1sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle.$




    And furthermore with




    $||m_1−m_2||^2=langle sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2,sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2 rangle = frac{1}{displaystyle n_1^2}sum_{i=1}^{n_1} ||x_i||^2 + frac{2}{displaystyle n_1^2}sum_{1leq i < jleq n_1} langle x_i, x_jrangle +frac{1}{displaystyle n_2^2}sum_{i=1}^{n_2} ||y_i||^2 + frac{2}{displaystyle n_2^2}sum_{1leq i < jleq n_2} langle y_i, y_jrangle - frac{2}{n_1n_2} sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle, $




    I obtain that




    $ frac{displaystyle d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




    Where is my error?










    share|cite|improve this question


























      up vote
      0
      down vote

      favorite









      up vote
      0
      down vote

      favorite











      In the following link is discussed the uniform Effect of K-means Clustering:



      https://www.springer.com/cda/content/document/cda_downloaddocument/9783642298066-c2.pdf?SGWID=0-0-45-1338325-p174318763



      He used the following equation:




      $ frac{displaystyle2 d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




      where




      $ d(C_1,C_2)=sum_{x_iin C_1}sum_{x_jin C_2}||x_i−x_j||^2$ with $ |C_1|=n_1$ and $|C_2 |=n_2$.




      I tried to prove this, but I do not get this. He uses the fact that




      $ d(C_1,C_1)=2(n_1-1)sum_{i=1}^{n_1} ||x_i||^2 -4 sum_{1leq i < j leq n_1}langle x_i,x_jrangle.$



      $ d(C_2,C_2)=2(n_2-1)sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq i < j leq n_2}langle y_i,y_jrangle.$



      $ d(C_1,C_2)=2n_2sum_{i=1}^{n_1} ||x_i||^2+2n_1sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle.$




      And furthermore with




      $||m_1−m_2||^2=langle sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2,sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2 rangle = frac{1}{displaystyle n_1^2}sum_{i=1}^{n_1} ||x_i||^2 + frac{2}{displaystyle n_1^2}sum_{1leq i < jleq n_1} langle x_i, x_jrangle +frac{1}{displaystyle n_2^2}sum_{i=1}^{n_2} ||y_i||^2 + frac{2}{displaystyle n_2^2}sum_{1leq i < jleq n_2} langle y_i, y_jrangle - frac{2}{n_1n_2} sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle, $




      I obtain that




      $ frac{displaystyle d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




      Where is my error?










      share|cite|improve this question















      In the following link is discussed the uniform Effect of K-means Clustering:



      https://www.springer.com/cda/content/document/cda_downloaddocument/9783642298066-c2.pdf?SGWID=0-0-45-1338325-p174318763



      He used the following equation:




      $ frac{displaystyle2 d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




      where




      $ d(C_1,C_2)=sum_{x_iin C_1}sum_{x_jin C_2}||x_i−x_j||^2$ with $ |C_1|=n_1$ and $|C_2 |=n_2$.




      I tried to prove this, but I do not get this. He uses the fact that




      $ d(C_1,C_1)=2(n_1-1)sum_{i=1}^{n_1} ||x_i||^2 -4 sum_{1leq i < j leq n_1}langle x_i,x_jrangle.$



      $ d(C_2,C_2)=2(n_2-1)sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq i < j leq n_2}langle y_i,y_jrangle.$



      $ d(C_1,C_2)=2n_2sum_{i=1}^{n_1} ||x_i||^2+2n_1sum_{i=1}^{n_2} ||y_i||^2 -4 sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle.$




      And furthermore with




      $||m_1−m_2||^2=langle sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2,sum_{i=1}^{n_1}x_i/n_1-sum_{j=1}^{n_1}y_j/n_2 rangle = frac{1}{displaystyle n_1^2}sum_{i=1}^{n_1} ||x_i||^2 + frac{2}{displaystyle n_1^2}sum_{1leq i < jleq n_1} langle x_i, x_jrangle +frac{1}{displaystyle n_2^2}sum_{i=1}^{n_2} ||y_i||^2 + frac{2}{displaystyle n_2^2}sum_{1leq i < jleq n_2} langle y_i, y_jrangle - frac{2}{n_1n_2} sum_{1leq ileq n_1}sum_{1leq jleq n_2}langle x_i,y_jrangle, $




      I obtain that




      $ frac{displaystyle d(C_1,C_2)}{displaystyle n_1n_2}=frac{displaystyle d(C_1,C_1)}{displaystyle n_1^2}+frac{displaystyle d(C_2,C_2)}{displaystyle n_2^2}+2||m_1−m_2||^2.$




      Where is my error?







      analysis vector-analysis inner-product-space machine-learning clustering






      share|cite|improve this question















      share|cite|improve this question













      share|cite|improve this question




      share|cite|improve this question








      edited 7 hours ago

























      asked 7 hours ago









      Patricio

      16711




      16711



























          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "69"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          noCode: true, onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














           

          draft saved


          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3006724%2funiform-effect-of-k-means-clustering%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown






























          active

          oldest

          votes













          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















           

          draft saved


          draft discarded



















































           


          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3006724%2funiform-effect-of-k-means-clustering%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          Berounka

          Sphinx de Gizeh

          Different font size/position of beamer's navigation symbols template's content depending on regular/plain...