Prove this property of softmax function?












2












$begingroup$


Consider the softmax function $f colon mathbb{R}^k rightarrow mathbb{R}^k $ defined by $f((x_1, ldots, x_n)) = (y_1, ldots, y_n)$ where $y_i = frac{e^{x_i}}{sum_j e^{x_j}}$.



Can you show that for every $x, Delta y,delta$, there exists $epsilon$ and $Delta x < delta$ such that $f(x + Delta x) = f(x) + epsilon cdot Delta y$? Also, is there a name for this property for general function? Assume there exists $x'$ such that $y + Delta y = f(x')$.










share|cite|improve this question











$endgroup$

















    2












    $begingroup$


    Consider the softmax function $f colon mathbb{R}^k rightarrow mathbb{R}^k $ defined by $f((x_1, ldots, x_n)) = (y_1, ldots, y_n)$ where $y_i = frac{e^{x_i}}{sum_j e^{x_j}}$.



    Can you show that for every $x, Delta y,delta$, there exists $epsilon$ and $Delta x < delta$ such that $f(x + Delta x) = f(x) + epsilon cdot Delta y$? Also, is there a name for this property for general function? Assume there exists $x'$ such that $y + Delta y = f(x')$.










    share|cite|improve this question











    $endgroup$















      2












      2








      2





      $begingroup$


      Consider the softmax function $f colon mathbb{R}^k rightarrow mathbb{R}^k $ defined by $f((x_1, ldots, x_n)) = (y_1, ldots, y_n)$ where $y_i = frac{e^{x_i}}{sum_j e^{x_j}}$.



      Can you show that for every $x, Delta y,delta$, there exists $epsilon$ and $Delta x < delta$ such that $f(x + Delta x) = f(x) + epsilon cdot Delta y$? Also, is there a name for this property for general function? Assume there exists $x'$ such that $y + Delta y = f(x')$.










      share|cite|improve this question











      $endgroup$




      Consider the softmax function $f colon mathbb{R}^k rightarrow mathbb{R}^k $ defined by $f((x_1, ldots, x_n)) = (y_1, ldots, y_n)$ where $y_i = frac{e^{x_i}}{sum_j e^{x_j}}$.



      Can you show that for every $x, Delta y,delta$, there exists $epsilon$ and $Delta x < delta$ such that $f(x + Delta x) = f(x) + epsilon cdot Delta y$? Also, is there a name for this property for general function? Assume there exists $x'$ such that $y + Delta y = f(x')$.







      real-analysis linear-algebra functional-analysis






      share|cite|improve this question















      share|cite|improve this question













      share|cite|improve this question




      share|cite|improve this question








      edited Feb 1 at 5:44







      listener

















      asked Jan 31 at 21:33









      listenerlistener

      205




      205






















          1 Answer
          1






          active

          oldest

          votes


















          0












          $begingroup$

          I'm not so sure that you can make that statement. By the construction of the softmax, the sum of its entries is equal to $1$, in other words:



          $$sum_{i=1}^k [f(x + Delta x)]_i = 1$$



          and



          $$sum_{i=1}^k [f(x)]_i = 1$$



          However, from what you've written,



          $$
          f(x+Delta x) = f(x) + epsilon Delta y
          $$



          It would imply that



          $$sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1$$



          which leads us to a contradiction if we sum over the entries of $f(x + Delta x)$:



          $$
          sum_{i=1}^k [f(x+Delta x)]_i = sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1
          $$






          share|cite|improve this answer









          $endgroup$













          • $begingroup$
            updated the question. I meant for any valid vector $Delta y$.
            $endgroup$
            – listener
            Feb 1 at 5:39












          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',
          autoActivateHeartbeat: false,
          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%2f3095494%2fprove-this-property-of-softmax-function%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          1 Answer
          1






          active

          oldest

          votes








          1 Answer
          1






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes









          0












          $begingroup$

          I'm not so sure that you can make that statement. By the construction of the softmax, the sum of its entries is equal to $1$, in other words:



          $$sum_{i=1}^k [f(x + Delta x)]_i = 1$$



          and



          $$sum_{i=1}^k [f(x)]_i = 1$$



          However, from what you've written,



          $$
          f(x+Delta x) = f(x) + epsilon Delta y
          $$



          It would imply that



          $$sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1$$



          which leads us to a contradiction if we sum over the entries of $f(x + Delta x)$:



          $$
          sum_{i=1}^k [f(x+Delta x)]_i = sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1
          $$






          share|cite|improve this answer









          $endgroup$













          • $begingroup$
            updated the question. I meant for any valid vector $Delta y$.
            $endgroup$
            – listener
            Feb 1 at 5:39
















          0












          $begingroup$

          I'm not so sure that you can make that statement. By the construction of the softmax, the sum of its entries is equal to $1$, in other words:



          $$sum_{i=1}^k [f(x + Delta x)]_i = 1$$



          and



          $$sum_{i=1}^k [f(x)]_i = 1$$



          However, from what you've written,



          $$
          f(x+Delta x) = f(x) + epsilon Delta y
          $$



          It would imply that



          $$sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1$$



          which leads us to a contradiction if we sum over the entries of $f(x + Delta x)$:



          $$
          sum_{i=1}^k [f(x+Delta x)]_i = sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1
          $$






          share|cite|improve this answer









          $endgroup$













          • $begingroup$
            updated the question. I meant for any valid vector $Delta y$.
            $endgroup$
            – listener
            Feb 1 at 5:39














          0












          0








          0





          $begingroup$

          I'm not so sure that you can make that statement. By the construction of the softmax, the sum of its entries is equal to $1$, in other words:



          $$sum_{i=1}^k [f(x + Delta x)]_i = 1$$



          and



          $$sum_{i=1}^k [f(x)]_i = 1$$



          However, from what you've written,



          $$
          f(x+Delta x) = f(x) + epsilon Delta y
          $$



          It would imply that



          $$sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1$$



          which leads us to a contradiction if we sum over the entries of $f(x + Delta x)$:



          $$
          sum_{i=1}^k [f(x+Delta x)]_i = sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1
          $$






          share|cite|improve this answer









          $endgroup$



          I'm not so sure that you can make that statement. By the construction of the softmax, the sum of its entries is equal to $1$, in other words:



          $$sum_{i=1}^k [f(x + Delta x)]_i = 1$$



          and



          $$sum_{i=1}^k [f(x)]_i = 1$$



          However, from what you've written,



          $$
          f(x+Delta x) = f(x) + epsilon Delta y
          $$



          It would imply that



          $$sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1$$



          which leads us to a contradiction if we sum over the entries of $f(x + Delta x)$:



          $$
          sum_{i=1}^k [f(x+Delta x)]_i = sum_{i=1}^k [f(x) + epsilon Delta y]_i > 1
          $$







          share|cite|improve this answer












          share|cite|improve this answer



          share|cite|improve this answer










          answered Feb 1 at 0:12









          Sean LeeSean Lee

          749214




          749214












          • $begingroup$
            updated the question. I meant for any valid vector $Delta y$.
            $endgroup$
            – listener
            Feb 1 at 5:39


















          • $begingroup$
            updated the question. I meant for any valid vector $Delta y$.
            $endgroup$
            – listener
            Feb 1 at 5:39
















          $begingroup$
          updated the question. I meant for any valid vector $Delta y$.
          $endgroup$
          – listener
          Feb 1 at 5:39




          $begingroup$
          updated the question. I meant for any valid vector $Delta y$.
          $endgroup$
          – listener
          Feb 1 at 5:39


















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Mathematics Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fmath.stackexchange.com%2fquestions%2f3095494%2fprove-this-property-of-softmax-function%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

          MongoDB - Not Authorized To Execute Command

          How to fix TextFormField cause rebuild widget in Flutter

          Npm cannot find a required file even through it is in the searched directory