What loss function to use when labels are probabilities? Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) Announcing the arrival of Valued Associate #679: Cesar Manara Unicorn Meta Zoo #1: Why another podcast?Why would neural networks be a particularly good framework for “embodied AI”?Understanding GAN Loss functionHelp with implementing Q-learning for a feedfoward network playing a video gameHow do I implement softmax forward propagation and backpropagation to replace sigmoid in a neural network?Gradient of hinge loss functionHow to understand marginal loglikelihood objective function as loss function (explanation of an article)?What is batch / batch size in neural networks?Comparing and studying Loss FunctionsLoss function spikesPredicting sine using LSTM: Small output range and delayed output?

What was the last x86 CPU that did not have the x87 floating-point unit built in?

How can you insert a "times/divide" symbol similar to the "plus/minus" (±) one?

Replacing HDD with SSD; what about non-APFS/APFS?

Fishing simulator

Is there a service that would inform me whenever a new direct route is scheduled from a given airport?

How to say that you spent the night with someone, you were only sleeping and nothing else?

Single author papers against my advisor's will?

Writing Thesis: Copying from published papers

How can I make names more distinctive without making them longer?

Estimate capacitor parameters

Are my PIs rude or am I just being too sensitive?

How is simplicity better than precision and clarity in prose?

Autumning in love

What can I do if my MacBook isn’t charging but already ran out?

Did the new image of black hole confirm the general theory of relativity?

How to set letter above or below the symbol?

When is phishing education going too far?

What do you call a plan that's an alternative plan in case your initial plan fails?

Can smartphones with the same camera sensor have different image quality?

Mortgage adviser recommends a longer term than necessary combined with overpayments

Who can trigger ship-wide alerts in Star Trek?

Unable to start mainnet node docker container

Need a suitable toxic chemical for a murder plot in my novel

What loss function to use when labels are probabilities?



What loss function to use when labels are probabilities?



Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
Announcing the arrival of Valued Associate #679: Cesar Manara
Unicorn Meta Zoo #1: Why another podcast?Why would neural networks be a particularly good framework for “embodied AI”?Understanding GAN Loss functionHelp with implementing Q-learning for a feedfoward network playing a video gameHow do I implement softmax forward propagation and backpropagation to replace sigmoid in a neural network?Gradient of hinge loss functionHow to understand marginal loglikelihood objective function as loss function (explanation of an article)?What is batch / batch size in neural networks?Comparing and studying Loss FunctionsLoss function spikesPredicting sine using LSTM: Small output range and delayed output?



.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;








2












$begingroup$


What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].



It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.



Would something like MSE (after applying softmax) make sense, or is there a better loss function?










share|improve this question







New contributor




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







$endgroup$


















    2












    $begingroup$


    What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].



    It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.



    Would something like MSE (after applying softmax) make sense, or is there a better loss function?










    share|improve this question







    New contributor




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







    $endgroup$














      2












      2








      2





      $begingroup$


      What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].



      It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.



      Would something like MSE (after applying softmax) make sense, or is there a better loss function?










      share|improve this question







      New contributor




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







      $endgroup$




      What loss function is most appropriate when training a model with target values that are probabilities? For example, I have a 3-output model with x=[some features] and y=[0.2, 0.3, 0.5].



      It seems like something like cross-entropy doesn't make sense here since it assumes that a single target is the correct label.



      Would something like MSE (after applying softmax) make sense, or is there a better loss function?







      neural-networks loss-functions probability-distribution






      share|improve this question







      New contributor




      Thomas Johnson 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




      Thomas Johnson 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






      New contributor




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









      asked 6 hours ago









      Thomas JohnsonThomas Johnson

      1133




      1133




      New contributor




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





      New contributor





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






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




















          1 Answer
          1






          active

          oldest

          votes


















          3












          $begingroup$

          Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.



          You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,



          $$H(p,q)=-sum_xin X p(x) log q(x).$$
          $ $



          Note that one-hot labels would mean that
          $$
          p(x) =
          begincases
          1 & textif x text is the true label\
          0 & textotherwise
          endcases$$



          which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:



          $$H(p,q) = -log q(x_label)$$






          share|improve this answer









          $endgroup$













            Your Answer








            StackExchange.ready(function()
            var channelOptions =
            tags: "".split(" "),
            id: "658"
            ;
            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
            ,
            noCode: true, onDemand: true,
            discardSelector: ".discard-answer"
            ,immediatelyShowMarkdownHelp:true
            );



            );






            Thomas Johnson 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%2fai.stackexchange.com%2fquestions%2f11816%2fwhat-loss-function-to-use-when-labels-are-probabilities%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









            3












            $begingroup$

            Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.



            You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,



            $$H(p,q)=-sum_xin X p(x) log q(x).$$
            $ $



            Note that one-hot labels would mean that
            $$
            p(x) =
            begincases
            1 & textif x text is the true label\
            0 & textotherwise
            endcases$$



            which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:



            $$H(p,q) = -log q(x_label)$$






            share|improve this answer









            $endgroup$

















              3












              $begingroup$

              Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.



              You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,



              $$H(p,q)=-sum_xin X p(x) log q(x).$$
              $ $



              Note that one-hot labels would mean that
              $$
              p(x) =
              begincases
              1 & textif x text is the true label\
              0 & textotherwise
              endcases$$



              which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:



              $$H(p,q) = -log q(x_label)$$






              share|improve this answer









              $endgroup$















                3












                3








                3





                $begingroup$

                Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.



                You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,



                $$H(p,q)=-sum_xin X p(x) log q(x).$$
                $ $



                Note that one-hot labels would mean that
                $$
                p(x) =
                begincases
                1 & textif x text is the true label\
                0 & textotherwise
                endcases$$



                which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:



                $$H(p,q) = -log q(x_label)$$






                share|improve this answer









                $endgroup$



                Actually, the cross-entropy loss function would be appropriate here, since it measures the "distance" between a distribution $q$ and the "true" distribution $p$.



                You are right, though, that using a loss function called "cross_entropy" in many APIs would be a mistake. This is because these functions, as you said, assume a one-hot label. You would need to use the general cross-entropy function,



                $$H(p,q)=-sum_xin X p(x) log q(x).$$
                $ $



                Note that one-hot labels would mean that
                $$
                p(x) =
                begincases
                1 & textif x text is the true label\
                0 & textotherwise
                endcases$$



                which causes the cross-entropy $H(p,q)$ to reduce to the form you're familiar with:



                $$H(p,q) = -log q(x_label)$$







                share|improve this answer












                share|improve this answer



                share|improve this answer










                answered 6 hours ago









                Philip RaeisghasemPhilip Raeisghasem

                988119




                988119




















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









                    draft saved

                    draft discarded


















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












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











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














                    Thanks for contributing an answer to Artificial Intelligence 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%2fai.stackexchange.com%2fquestions%2f11816%2fwhat-loss-function-to-use-when-labels-are-probabilities%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

                    名間水力發電廠 目录 沿革 設施 鄰近設施 註釋 外部連結 导航菜单23°50′10″N 120°42′41″E / 23.83611°N 120.71139°E / 23.83611; 120.7113923°50′10″N 120°42′41″E / 23.83611°N 120.71139°E / 23.83611; 120.71139計畫概要原始内容臺灣第一座BOT 模式開發的水力發電廠-名間水力電廠名間水力發電廠 水利署首件BOT案原始内容《小檔案》名間電廠 首座BOT水力發電廠原始内容名間電廠BOT - 經濟部水利署中區水資源局

                    Prove that NP is closed under karp reduction?Space(n) not closed under Karp reductions - what about NTime(n)?Class P is closed under rotation?Prove or disprove that $NL$ is closed under polynomial many-one reductions$mathbfNC_2$ is closed under log-space reductionOn Karp reductionwhen can I know if a class (complexity) is closed under reduction (cook/karp)Check if class $PSPACE$ is closed under polyonomially space reductionIs NPSPACE also closed under polynomial-time reduction and under log-space reduction?Prove PSPACE is closed under complement?Prove PSPACE is closed under union?

                    Is my guitar’s action too high? Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30pm US/Eastern)Strings too stiff on a recently purchased acoustic guitar | Cort AD880CEIs the action of my guitar really high?Μy little finger is too weak to play guitarWith guitar, how long should I give my fingers to strengthen / callous?When playing a fret the guitar sounds mutedPlaying (Barre) chords up the guitar neckI think my guitar strings are wound too tight and I can't play barre chordsF barre chord on an SG guitarHow to find to the right strings of a barre chord by feel?High action on higher fret on my steel acoustic guitar