Find Lipschtiz constant for a function in matrix











up vote
0
down vote

favorite












I have the following function in $X in R^{n times k}$



$$f(X) = -4A XLambda_1 + 4(XLambda_1 X^T XLambda_1) - 4A^TXYLambda_2Y^T + 4XYLambda_2Y^TX^TXYLambda_2Y^T$$



where $A in R^{n times n}$, $Y in R^{k times k1}$, $Lambda_1 in R^{k times k}$ and $Lambda_2 in R^{k1 times k1}$, and $Lambda_1 , Lambda_2$ are diagonal matrices. How can I find Lipschitz constant of the above function with respect to frobenious norm? Would it be possible to find local Lipschitz constant I know ||X||? The f function is gradient with respect to X and I am trying to do a gradient descent, so, I will have bounds on ||X||.










share|cite|improve this question




















  • 1




    There is no global Lipschitz constant for $f$.
    – copper.hat
    Nov 19 at 0:28










  • @copper.hat Why is there no global Lipschitz?
    – Dushyant Sahoo
    Nov 19 at 1:05










  • Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
    – copper.hat
    Nov 19 at 1:11










  • @copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
    – Dushyant Sahoo
    Nov 19 at 1:31






  • 1




    I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
    – copper.hat
    Nov 19 at 1:55















up vote
0
down vote

favorite












I have the following function in $X in R^{n times k}$



$$f(X) = -4A XLambda_1 + 4(XLambda_1 X^T XLambda_1) - 4A^TXYLambda_2Y^T + 4XYLambda_2Y^TX^TXYLambda_2Y^T$$



where $A in R^{n times n}$, $Y in R^{k times k1}$, $Lambda_1 in R^{k times k}$ and $Lambda_2 in R^{k1 times k1}$, and $Lambda_1 , Lambda_2$ are diagonal matrices. How can I find Lipschitz constant of the above function with respect to frobenious norm? Would it be possible to find local Lipschitz constant I know ||X||? The f function is gradient with respect to X and I am trying to do a gradient descent, so, I will have bounds on ||X||.










share|cite|improve this question




















  • 1




    There is no global Lipschitz constant for $f$.
    – copper.hat
    Nov 19 at 0:28










  • @copper.hat Why is there no global Lipschitz?
    – Dushyant Sahoo
    Nov 19 at 1:05










  • Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
    – copper.hat
    Nov 19 at 1:11










  • @copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
    – Dushyant Sahoo
    Nov 19 at 1:31






  • 1




    I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
    – copper.hat
    Nov 19 at 1:55













up vote
0
down vote

favorite









up vote
0
down vote

favorite











I have the following function in $X in R^{n times k}$



$$f(X) = -4A XLambda_1 + 4(XLambda_1 X^T XLambda_1) - 4A^TXYLambda_2Y^T + 4XYLambda_2Y^TX^TXYLambda_2Y^T$$



where $A in R^{n times n}$, $Y in R^{k times k1}$, $Lambda_1 in R^{k times k}$ and $Lambda_2 in R^{k1 times k1}$, and $Lambda_1 , Lambda_2$ are diagonal matrices. How can I find Lipschitz constant of the above function with respect to frobenious norm? Would it be possible to find local Lipschitz constant I know ||X||? The f function is gradient with respect to X and I am trying to do a gradient descent, so, I will have bounds on ||X||.










share|cite|improve this question















I have the following function in $X in R^{n times k}$



$$f(X) = -4A XLambda_1 + 4(XLambda_1 X^T XLambda_1) - 4A^TXYLambda_2Y^T + 4XYLambda_2Y^TX^TXYLambda_2Y^T$$



where $A in R^{n times n}$, $Y in R^{k times k1}$, $Lambda_1 in R^{k times k}$ and $Lambda_2 in R^{k1 times k1}$, and $Lambda_1 , Lambda_2$ are diagonal matrices. How can I find Lipschitz constant of the above function with respect to frobenious norm? Would it be possible to find local Lipschitz constant I know ||X||? The f function is gradient with respect to X and I am trying to do a gradient descent, so, I will have bounds on ||X||.







matrices analysis lipschitz-functions






share|cite|improve this question















share|cite|improve this question













share|cite|improve this question




share|cite|improve this question








edited Nov 19 at 2:04

























asked Nov 19 at 0:25









Dushyant Sahoo

548




548








  • 1




    There is no global Lipschitz constant for $f$.
    – copper.hat
    Nov 19 at 0:28










  • @copper.hat Why is there no global Lipschitz?
    – Dushyant Sahoo
    Nov 19 at 1:05










  • Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
    – copper.hat
    Nov 19 at 1:11










  • @copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
    – Dushyant Sahoo
    Nov 19 at 1:31






  • 1




    I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
    – copper.hat
    Nov 19 at 1:55














  • 1




    There is no global Lipschitz constant for $f$.
    – copper.hat
    Nov 19 at 0:28










  • @copper.hat Why is there no global Lipschitz?
    – Dushyant Sahoo
    Nov 19 at 1:05










  • Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
    – copper.hat
    Nov 19 at 1:11










  • @copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
    – Dushyant Sahoo
    Nov 19 at 1:31






  • 1




    I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
    – copper.hat
    Nov 19 at 1:55








1




1




There is no global Lipschitz constant for $f$.
– copper.hat
Nov 19 at 0:28




There is no global Lipschitz constant for $f$.
– copper.hat
Nov 19 at 0:28












@copper.hat Why is there no global Lipschitz?
– Dushyant Sahoo
Nov 19 at 1:05




@copper.hat Why is there no global Lipschitz?
– Dushyant Sahoo
Nov 19 at 1:05












Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
– copper.hat
Nov 19 at 1:11




Well, it depends on the actual values of the matrices above, but consider the formula for scalars, there is an $X^3$ term which is not Lipschitz.
– copper.hat
Nov 19 at 1:11












@copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
– Dushyant Sahoo
Nov 19 at 1:31




@copper.hat What if I know ||X||? The $f$ function is gradient with respect to $X$ and I am trying to do a gradient descent, so, I will have bounds on ||X||.
– Dushyant Sahoo
Nov 19 at 1:31




1




1




I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
– copper.hat
Nov 19 at 1:55




I don't know what to say. In general, the function is not globally Lipschitz. On any bounded set you can find a local Lipschitz constant. One way is to find the derivative of $f$ with respect to $X$ and bound the derivative.
– copper.hat
Nov 19 at 1:55















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',
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%2f3004328%2ffind-lipschtiz-constant-for-a-function-in-matrix%23new-answer', 'question_page');
}
);

Post as a guest















Required, but never shown






























active

oldest

votes













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.





Some of your past answers have not been well-received, and you're in danger of being blocked from answering.


Please pay close attention to the following guidance:


  • 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.


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%2f3004328%2ffind-lipschtiz-constant-for-a-function-in-matrix%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

Aardman Animations

Are they similar matrix

“minimization” problem in Euclidean space related to orthonormal basis