0
$\begingroup$

I am a newbie learning about Kernel density estimations

How density can be estimated for data with the number of samples equal to the number of features. Is it really useful to do density estimation for high dimensional data without reducing dimensions?

My intuition is if we have such data and if we estimate distribution then large values (huge number of values) fall under the distribution.

let me know whether I'm correct or wrong

$\endgroup$
5
  • $\begingroup$ What kind of sparse data you have in mind? $\endgroup$
    – Tim
    Jun 22, 2020 at 12:07
  • $\begingroup$ If dimensions of data are more then data samples would be visually far away so in such situations can we try to use density estimation is it useful? My intuition is if we such data and if we estimate distribution then large values (huge number of values) fall under the distribution. let me know whether I'm correct or wrong $\endgroup$ Jun 22, 2020 at 12:15
  • 1
    $\begingroup$ So by "sparse data" you mean more columns then rows? This is not what sparse data is, you should edit your question to make it clear what exactly do you mean, otherwise it may be hard to answer. $\endgroup$
    – Tim
    Jun 22, 2020 at 12:19
  • $\begingroup$ I hope now I made it more clear $\endgroup$ Jun 22, 2020 at 12:34
  • $\begingroup$ Thanks, now it's more clear. $\endgroup$
    – Tim
    Jun 22, 2020 at 12:41

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.