Confusion about the notation of Rademacher Complexity












0












$begingroup$


The online book:
https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf



In "Understanding Machine Learning:From Theory to Algorithms" by Shai Shalev-Shwartz and Shai Ben-David, Chapter 26 "Rademacher Complexity",
part 26.1, for reasons of notational brevity, the set $mathcal{F}$ is defined as:
$$
mathcal{F} := mathcal{l} circ mathcal{H} := {z mapsto l(h,z): hin mathcal{H} }
$$



Where $l$ is a loss function, $mathcal{H}$ is the hypothesis space, and $z$ refers to a tuple $(x,y)$.



I'm unsure of how to interpret this.



Does it mean "the set of functions that map $mathcal{Z}$ to $mathbb{R}$ via the loss function $l$ and any $hin mathcal{H}$?" If so, isn't this just the loss function $l$ and thus shouldn't the mapping be from $mathcal{Z} times mathcal{H}$ to $mathbb{R}$ instead?



Alternatively, could this mean "the set of functions $f_h:mathcal{Z} to mathbb{R}$ where $hin mathcal{H}$"? But seeing as the dependency on $h$ is not expressed in subsequent parts of the literature, I have my doubts about this.



I would really appreciate it if someone could clarify this.










share|cite|improve this question









$endgroup$

















    0












    $begingroup$


    The online book:
    https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf



    In "Understanding Machine Learning:From Theory to Algorithms" by Shai Shalev-Shwartz and Shai Ben-David, Chapter 26 "Rademacher Complexity",
    part 26.1, for reasons of notational brevity, the set $mathcal{F}$ is defined as:
    $$
    mathcal{F} := mathcal{l} circ mathcal{H} := {z mapsto l(h,z): hin mathcal{H} }
    $$



    Where $l$ is a loss function, $mathcal{H}$ is the hypothesis space, and $z$ refers to a tuple $(x,y)$.



    I'm unsure of how to interpret this.



    Does it mean "the set of functions that map $mathcal{Z}$ to $mathbb{R}$ via the loss function $l$ and any $hin mathcal{H}$?" If so, isn't this just the loss function $l$ and thus shouldn't the mapping be from $mathcal{Z} times mathcal{H}$ to $mathbb{R}$ instead?



    Alternatively, could this mean "the set of functions $f_h:mathcal{Z} to mathbb{R}$ where $hin mathcal{H}$"? But seeing as the dependency on $h$ is not expressed in subsequent parts of the literature, I have my doubts about this.



    I would really appreciate it if someone could clarify this.










    share|cite|improve this question









    $endgroup$















      0












      0








      0





      $begingroup$


      The online book:
      https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf



      In "Understanding Machine Learning:From Theory to Algorithms" by Shai Shalev-Shwartz and Shai Ben-David, Chapter 26 "Rademacher Complexity",
      part 26.1, for reasons of notational brevity, the set $mathcal{F}$ is defined as:
      $$
      mathcal{F} := mathcal{l} circ mathcal{H} := {z mapsto l(h,z): hin mathcal{H} }
      $$



      Where $l$ is a loss function, $mathcal{H}$ is the hypothesis space, and $z$ refers to a tuple $(x,y)$.



      I'm unsure of how to interpret this.



      Does it mean "the set of functions that map $mathcal{Z}$ to $mathbb{R}$ via the loss function $l$ and any $hin mathcal{H}$?" If so, isn't this just the loss function $l$ and thus shouldn't the mapping be from $mathcal{Z} times mathcal{H}$ to $mathbb{R}$ instead?



      Alternatively, could this mean "the set of functions $f_h:mathcal{Z} to mathbb{R}$ where $hin mathcal{H}$"? But seeing as the dependency on $h$ is not expressed in subsequent parts of the literature, I have my doubts about this.



      I would really appreciate it if someone could clarify this.










      share|cite|improve this question









      $endgroup$




      The online book:
      https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf



      In "Understanding Machine Learning:From Theory to Algorithms" by Shai Shalev-Shwartz and Shai Ben-David, Chapter 26 "Rademacher Complexity",
      part 26.1, for reasons of notational brevity, the set $mathcal{F}$ is defined as:
      $$
      mathcal{F} := mathcal{l} circ mathcal{H} := {z mapsto l(h,z): hin mathcal{H} }
      $$



      Where $l$ is a loss function, $mathcal{H}$ is the hypothesis space, and $z$ refers to a tuple $(x,y)$.



      I'm unsure of how to interpret this.



      Does it mean "the set of functions that map $mathcal{Z}$ to $mathbb{R}$ via the loss function $l$ and any $hin mathcal{H}$?" If so, isn't this just the loss function $l$ and thus shouldn't the mapping be from $mathcal{Z} times mathcal{H}$ to $mathbb{R}$ instead?



      Alternatively, could this mean "the set of functions $f_h:mathcal{Z} to mathbb{R}$ where $hin mathcal{H}$"? But seeing as the dependency on $h$ is not expressed in subsequent parts of the literature, I have my doubts about this.



      I would really appreciate it if someone could clarify this.







      machine-learning rademacher-distribution






      share|cite|improve this question













      share|cite|improve this question











      share|cite|improve this question




      share|cite|improve this question










      asked Dec 3 '18 at 0:50









      Sean LeeSean Lee

      1578




      1578






















          0






          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',
          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%2f3023450%2fconfusion-about-the-notation-of-rademacher-complexity%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          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%2f3023450%2fconfusion-about-the-notation-of-rademacher-complexity%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

          Ellipse (mathématiques)

          Quarter-circle Tiles

          Mont Emei