Variance of Monte Carlo integration with importance sampling





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







3












$begingroup$


I am following these lecture slides on Monte Carlo integration with importance sampling. I am just implementing a very simple example: $int_{0}^{1} e^{x}dx$. For the importance sampling version, I rewrite $int_{0}^{1} e^{x}dx = int_{0}^{1} e^{x}/p(x)cdot p(x)dx$ where $p(x) = 2.5x^{1.5}$. Then



$$hat{I} = frac{1}{N}sum_{j=1}^{N} frac{f(x_{j})}{p(x_{j})},$$



where $x_{j}$ are sampled from $p(x_{j})$ (I use an inverse transform method here). For the variance, I have $sigma_{I}^{2} = hat{sigma}_{I}^{2}/N$ and



$$hat{sigma}_{I}^{2} = frac{1}{N} sum_{j=1}^{N} frac{f(x_{j})^{2}}{g(x_{j})^{2}} - hat{I}^{2}.$$



I know I should expected the variance to decrease with importance sampling, but a plot of the variance with $N$ shows that not much happens. Can anyone explain to me what I'm doing incorrectly? I'm not sure how the they are able to achieve such a drastic decrease in variance in the lecture slides.



enter image description here










share|cite|improve this question









$endgroup$



















    3












    $begingroup$


    I am following these lecture slides on Monte Carlo integration with importance sampling. I am just implementing a very simple example: $int_{0}^{1} e^{x}dx$. For the importance sampling version, I rewrite $int_{0}^{1} e^{x}dx = int_{0}^{1} e^{x}/p(x)cdot p(x)dx$ where $p(x) = 2.5x^{1.5}$. Then



    $$hat{I} = frac{1}{N}sum_{j=1}^{N} frac{f(x_{j})}{p(x_{j})},$$



    where $x_{j}$ are sampled from $p(x_{j})$ (I use an inverse transform method here). For the variance, I have $sigma_{I}^{2} = hat{sigma}_{I}^{2}/N$ and



    $$hat{sigma}_{I}^{2} = frac{1}{N} sum_{j=1}^{N} frac{f(x_{j})^{2}}{g(x_{j})^{2}} - hat{I}^{2}.$$



    I know I should expected the variance to decrease with importance sampling, but a plot of the variance with $N$ shows that not much happens. Can anyone explain to me what I'm doing incorrectly? I'm not sure how the they are able to achieve such a drastic decrease in variance in the lecture slides.



    enter image description here










    share|cite|improve this question









    $endgroup$















      3












      3








      3


      3



      $begingroup$


      I am following these lecture slides on Monte Carlo integration with importance sampling. I am just implementing a very simple example: $int_{0}^{1} e^{x}dx$. For the importance sampling version, I rewrite $int_{0}^{1} e^{x}dx = int_{0}^{1} e^{x}/p(x)cdot p(x)dx$ where $p(x) = 2.5x^{1.5}$. Then



      $$hat{I} = frac{1}{N}sum_{j=1}^{N} frac{f(x_{j})}{p(x_{j})},$$



      where $x_{j}$ are sampled from $p(x_{j})$ (I use an inverse transform method here). For the variance, I have $sigma_{I}^{2} = hat{sigma}_{I}^{2}/N$ and



      $$hat{sigma}_{I}^{2} = frac{1}{N} sum_{j=1}^{N} frac{f(x_{j})^{2}}{g(x_{j})^{2}} - hat{I}^{2}.$$



      I know I should expected the variance to decrease with importance sampling, but a plot of the variance with $N$ shows that not much happens. Can anyone explain to me what I'm doing incorrectly? I'm not sure how the they are able to achieve such a drastic decrease in variance in the lecture slides.



      enter image description here










      share|cite|improve this question









      $endgroup$




      I am following these lecture slides on Monte Carlo integration with importance sampling. I am just implementing a very simple example: $int_{0}^{1} e^{x}dx$. For the importance sampling version, I rewrite $int_{0}^{1} e^{x}dx = int_{0}^{1} e^{x}/p(x)cdot p(x)dx$ where $p(x) = 2.5x^{1.5}$. Then



      $$hat{I} = frac{1}{N}sum_{j=1}^{N} frac{f(x_{j})}{p(x_{j})},$$



      where $x_{j}$ are sampled from $p(x_{j})$ (I use an inverse transform method here). For the variance, I have $sigma_{I}^{2} = hat{sigma}_{I}^{2}/N$ and



      $$hat{sigma}_{I}^{2} = frac{1}{N} sum_{j=1}^{N} frac{f(x_{j})^{2}}{g(x_{j})^{2}} - hat{I}^{2}.$$



      I know I should expected the variance to decrease with importance sampling, but a plot of the variance with $N$ shows that not much happens. Can anyone explain to me what I'm doing incorrectly? I'm not sure how the they are able to achieve such a drastic decrease in variance in the lecture slides.



      enter image description here







      monte-carlo integral importance-sampling






      share|cite|improve this question













      share|cite|improve this question











      share|cite|improve this question




      share|cite|improve this question










      asked Apr 1 at 18:26









      user1799323user1799323

      1234




      1234






















          1 Answer
          1






          active

          oldest

          votes


















          3












          $begingroup$

          enter image description hereThis is a good illustration of the dangers of importance sampling: while
          $$int_0^1 frac{e^x}{p(x)}, p(x)text{d} x = int_0^1 e^x text{d} x = I$$
          shows that $hat{I}_N$ is an unbiased estimator of $I$, this estimator does not have a finite variance since
          $$int_0^1 left(frac{e^x}{p(x)}right)^2, p(x)text{d} x = int_0^1 frac{e^{2x}}{2.5 x^{1.5}} text{d} x = infty$$
          since the integral diverges in $x=0$. For instance,



          > x=runif(1e7)^{1/2.5}
          > range(exp(x)/x^{1.5})
          [1] 2.718282 83403.685972


          shows that the weights can widely differ. I am not surprised at the figures reported in the above slides since



           > mean(exp(x)/x^{1.5})/2.5
          [1] 1.717576
          > var(exp(x)/x^{1.5})/(2.5)^2/1e7
          [1] 2.070953e-06


          but the empirical variance is rarely able to spot infinite variance importance sampling. (The graph shows that both the standard Monte Carlo estimate and the importance sampling version see the empirical standard deviation is decreasing as $N^{-1/2}$.)






          share|cite|improve this answer











          $endgroup$














            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: "65"
            };
            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
            });


            }
            });














            draft saved

            draft discarded


















            StackExchange.ready(
            function () {
            StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstats.stackexchange.com%2fquestions%2f400628%2fvariance-of-monte-carlo-integration-with-importance-sampling%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












            $begingroup$

            enter image description hereThis is a good illustration of the dangers of importance sampling: while
            $$int_0^1 frac{e^x}{p(x)}, p(x)text{d} x = int_0^1 e^x text{d} x = I$$
            shows that $hat{I}_N$ is an unbiased estimator of $I$, this estimator does not have a finite variance since
            $$int_0^1 left(frac{e^x}{p(x)}right)^2, p(x)text{d} x = int_0^1 frac{e^{2x}}{2.5 x^{1.5}} text{d} x = infty$$
            since the integral diverges in $x=0$. For instance,



            > x=runif(1e7)^{1/2.5}
            > range(exp(x)/x^{1.5})
            [1] 2.718282 83403.685972


            shows that the weights can widely differ. I am not surprised at the figures reported in the above slides since



             > mean(exp(x)/x^{1.5})/2.5
            [1] 1.717576
            > var(exp(x)/x^{1.5})/(2.5)^2/1e7
            [1] 2.070953e-06


            but the empirical variance is rarely able to spot infinite variance importance sampling. (The graph shows that both the standard Monte Carlo estimate and the importance sampling version see the empirical standard deviation is decreasing as $N^{-1/2}$.)






            share|cite|improve this answer











            $endgroup$


















              3












              $begingroup$

              enter image description hereThis is a good illustration of the dangers of importance sampling: while
              $$int_0^1 frac{e^x}{p(x)}, p(x)text{d} x = int_0^1 e^x text{d} x = I$$
              shows that $hat{I}_N$ is an unbiased estimator of $I$, this estimator does not have a finite variance since
              $$int_0^1 left(frac{e^x}{p(x)}right)^2, p(x)text{d} x = int_0^1 frac{e^{2x}}{2.5 x^{1.5}} text{d} x = infty$$
              since the integral diverges in $x=0$. For instance,



              > x=runif(1e7)^{1/2.5}
              > range(exp(x)/x^{1.5})
              [1] 2.718282 83403.685972


              shows that the weights can widely differ. I am not surprised at the figures reported in the above slides since



               > mean(exp(x)/x^{1.5})/2.5
              [1] 1.717576
              > var(exp(x)/x^{1.5})/(2.5)^2/1e7
              [1] 2.070953e-06


              but the empirical variance is rarely able to spot infinite variance importance sampling. (The graph shows that both the standard Monte Carlo estimate and the importance sampling version see the empirical standard deviation is decreasing as $N^{-1/2}$.)






              share|cite|improve this answer











              $endgroup$
















                3












                3








                3





                $begingroup$

                enter image description hereThis is a good illustration of the dangers of importance sampling: while
                $$int_0^1 frac{e^x}{p(x)}, p(x)text{d} x = int_0^1 e^x text{d} x = I$$
                shows that $hat{I}_N$ is an unbiased estimator of $I$, this estimator does not have a finite variance since
                $$int_0^1 left(frac{e^x}{p(x)}right)^2, p(x)text{d} x = int_0^1 frac{e^{2x}}{2.5 x^{1.5}} text{d} x = infty$$
                since the integral diverges in $x=0$. For instance,



                > x=runif(1e7)^{1/2.5}
                > range(exp(x)/x^{1.5})
                [1] 2.718282 83403.685972


                shows that the weights can widely differ. I am not surprised at the figures reported in the above slides since



                 > mean(exp(x)/x^{1.5})/2.5
                [1] 1.717576
                > var(exp(x)/x^{1.5})/(2.5)^2/1e7
                [1] 2.070953e-06


                but the empirical variance is rarely able to spot infinite variance importance sampling. (The graph shows that both the standard Monte Carlo estimate and the importance sampling version see the empirical standard deviation is decreasing as $N^{-1/2}$.)






                share|cite|improve this answer











                $endgroup$



                enter image description hereThis is a good illustration of the dangers of importance sampling: while
                $$int_0^1 frac{e^x}{p(x)}, p(x)text{d} x = int_0^1 e^x text{d} x = I$$
                shows that $hat{I}_N$ is an unbiased estimator of $I$, this estimator does not have a finite variance since
                $$int_0^1 left(frac{e^x}{p(x)}right)^2, p(x)text{d} x = int_0^1 frac{e^{2x}}{2.5 x^{1.5}} text{d} x = infty$$
                since the integral diverges in $x=0$. For instance,



                > x=runif(1e7)^{1/2.5}
                > range(exp(x)/x^{1.5})
                [1] 2.718282 83403.685972


                shows that the weights can widely differ. I am not surprised at the figures reported in the above slides since



                 > mean(exp(x)/x^{1.5})/2.5
                [1] 1.717576
                > var(exp(x)/x^{1.5})/(2.5)^2/1e7
                [1] 2.070953e-06


                but the empirical variance is rarely able to spot infinite variance importance sampling. (The graph shows that both the standard Monte Carlo estimate and the importance sampling version see the empirical standard deviation is decreasing as $N^{-1/2}$.)







                share|cite|improve this answer














                share|cite|improve this answer



                share|cite|improve this answer








                edited Apr 1 at 19:02

























                answered Apr 1 at 18:44









                Xi'anXi'an

                59.2k897366




                59.2k897366






























                    draft saved

                    draft discarded




















































                    Thanks for contributing an answer to Cross Validated!


                    • 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%2fstats.stackexchange.com%2fquestions%2f400628%2fvariance-of-monte-carlo-integration-with-importance-sampling%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

                    Plaza Victoria

                    Puebla de Zaragoza

                    Musa