ML algorithms for regression in the case of label noise with a known distribution?












0












$begingroup$


I'm pretty new to machine learning, and I am interested in some ideas for algorithms or references for papers for using a ML algorithm for regression when the labeled data has label noise with a known distribution.



I am working on a problem where I have raw time-series data from a scientific instrument, and I'd like to associate each measurement with a scalar value that represents a physical parameter associated with that sample. I am starting with a labeled training data set in which each sample is associated with a discrete number $n_{0}, n_{1}, ..., n_{m} in mathbb{R} $. However, the actual scalar values for the physical parameter associated with the samples in the training data set labeled by $n_{i}$ are actually normally distributed about the value $n_{i}$ (e.g. the scalar values of these samples are drawn from the distribution $n_{i}+mathcal{N}(mu_{i},,sigma_{i}^{2})$ rather than all being exactly $n_{i}$ but because of the limitations of my experimental data I only know they are near $n_{i}$). I also know the values of $mu_{i}$ and $sigma_{i}$ for each of my $m+1$ labels.



Ideally I would like to come up with a way to predict any scalar value between $n_{0}$ and $n_{m}$ for new samples that I would test (not just the discrete values represented by the $m+1$ labels in my training data set that I've measured). What would be the best way to approach this kind of problem?










share|improve this question









New contributor




KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    0












    $begingroup$


    I'm pretty new to machine learning, and I am interested in some ideas for algorithms or references for papers for using a ML algorithm for regression when the labeled data has label noise with a known distribution.



    I am working on a problem where I have raw time-series data from a scientific instrument, and I'd like to associate each measurement with a scalar value that represents a physical parameter associated with that sample. I am starting with a labeled training data set in which each sample is associated with a discrete number $n_{0}, n_{1}, ..., n_{m} in mathbb{R} $. However, the actual scalar values for the physical parameter associated with the samples in the training data set labeled by $n_{i}$ are actually normally distributed about the value $n_{i}$ (e.g. the scalar values of these samples are drawn from the distribution $n_{i}+mathcal{N}(mu_{i},,sigma_{i}^{2})$ rather than all being exactly $n_{i}$ but because of the limitations of my experimental data I only know they are near $n_{i}$). I also know the values of $mu_{i}$ and $sigma_{i}$ for each of my $m+1$ labels.



    Ideally I would like to come up with a way to predict any scalar value between $n_{0}$ and $n_{m}$ for new samples that I would test (not just the discrete values represented by the $m+1$ labels in my training data set that I've measured). What would be the best way to approach this kind of problem?










    share|improve this question









    New contributor




    KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      0












      0








      0





      $begingroup$


      I'm pretty new to machine learning, and I am interested in some ideas for algorithms or references for papers for using a ML algorithm for regression when the labeled data has label noise with a known distribution.



      I am working on a problem where I have raw time-series data from a scientific instrument, and I'd like to associate each measurement with a scalar value that represents a physical parameter associated with that sample. I am starting with a labeled training data set in which each sample is associated with a discrete number $n_{0}, n_{1}, ..., n_{m} in mathbb{R} $. However, the actual scalar values for the physical parameter associated with the samples in the training data set labeled by $n_{i}$ are actually normally distributed about the value $n_{i}$ (e.g. the scalar values of these samples are drawn from the distribution $n_{i}+mathcal{N}(mu_{i},,sigma_{i}^{2})$ rather than all being exactly $n_{i}$ but because of the limitations of my experimental data I only know they are near $n_{i}$). I also know the values of $mu_{i}$ and $sigma_{i}$ for each of my $m+1$ labels.



      Ideally I would like to come up with a way to predict any scalar value between $n_{0}$ and $n_{m}$ for new samples that I would test (not just the discrete values represented by the $m+1$ labels in my training data set that I've measured). What would be the best way to approach this kind of problem?










      share|improve this question









      New contributor




      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I'm pretty new to machine learning, and I am interested in some ideas for algorithms or references for papers for using a ML algorithm for regression when the labeled data has label noise with a known distribution.



      I am working on a problem where I have raw time-series data from a scientific instrument, and I'd like to associate each measurement with a scalar value that represents a physical parameter associated with that sample. I am starting with a labeled training data set in which each sample is associated with a discrete number $n_{0}, n_{1}, ..., n_{m} in mathbb{R} $. However, the actual scalar values for the physical parameter associated with the samples in the training data set labeled by $n_{i}$ are actually normally distributed about the value $n_{i}$ (e.g. the scalar values of these samples are drawn from the distribution $n_{i}+mathcal{N}(mu_{i},,sigma_{i}^{2})$ rather than all being exactly $n_{i}$ but because of the limitations of my experimental data I only know they are near $n_{i}$). I also know the values of $mu_{i}$ and $sigma_{i}$ for each of my $m+1$ labels.



      Ideally I would like to come up with a way to predict any scalar value between $n_{0}$ and $n_{m}$ for new samples that I would test (not just the discrete values represented by the $m+1$ labels in my training data set that I've measured). What would be the best way to approach this kind of problem?







      machine-learning regression multilabel-classification labels






      share|improve this question









      New contributor




      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question









      New contributor




      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question








      edited 2 mins ago







      KDL













      New contributor




      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 53 mins ago









      KDLKDL

      11




      11




      New contributor




      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      KDL is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          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: "557"
          };
          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: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          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
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });






          KDL is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44539%2fml-algorithms-for-regression-in-the-case-of-label-noise-with-a-known-distributio%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








          KDL is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          KDL is a new contributor. Be nice, and check out our Code of Conduct.













          KDL is a new contributor. Be nice, and check out our Code of Conduct.












          KDL is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Data Science 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%2fdatascience.stackexchange.com%2fquestions%2f44539%2fml-algorithms-for-regression-in-the-case-of-label-noise-with-a-known-distributio%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

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana