29
$\begingroup$

I am interested in knowing what really happens in Hellinger Distance (in simple terms). Furthermore, I am also interested in knowing what are types of problems that we can use Hellinger Distance? What are the benefits of using Hellinger Distance?

$\endgroup$
8
  • 13
    $\begingroup$ The Hellinger distance is a probabilistic analog of the Euclidean distance. A salient property is its symmetry, as a metric. Such mathematical properties are useful if you are writing a paper and you need a distance function that possesses certain properties to make your proof possible. In application, someone might discover that one metric produces nicer or better results than another for a certain task; e.g., the Wasserstein distance is all the rage in generative adversarial networks $\endgroup$
    – Emre
    Aug 31, 2017 at 5:43
  • $\begingroup$ Thank you for the comment. I came across this question, which is quite similar to the question I have now. datascience.stackexchange.com/questions/22324/… Please let me know, why the answer says Hellinger Distance is suitable? $\endgroup$ Aug 31, 2017 at 5:59
  • 3
    $\begingroup$ Probably to visualize the topics in a metric space. Another nice property is that the Hellinger distance is finite for distributions with different support. It is good that you are asking these questions. I suggest trying different metrics for yourself and observing the results. $\endgroup$
    – Emre
    Aug 31, 2017 at 6:06
  • $\begingroup$ Thanks. its a good link. helps a lot. But is Hellinger distance only limited to topics derived from Latent Dirichlet Allocation (LDA) as mentioned in the link? $\endgroup$ Aug 31, 2017 at 6:11
  • 2
    $\begingroup$ No, it has no inherent connection to LDA. $\endgroup$
    – Emre
    Aug 31, 2017 at 6:12

1 Answer 1

12
$\begingroup$

Hellinger distance is a metric to measure the difference between two probability distributions. It is the probabilistic analog of Euclidean distance.

Given two probability distributions, $P$ and $Q$, Hellinger distance is defined as:

$$h(P,Q) = \frac1{\sqrt2}\cdot \|\sqrt{P}-\sqrt{Q}\|_2$$

It is useful when quantifying the difference between two probability distributions. For example, if you estimate a distribution for users and non-users of a service. If the Hellinger distance is small between those groups for some features, then those features are not statistically useful for segmentation.

$\endgroup$
1
  • 6
    $\begingroup$ (also for @Emre) where does the claim that hellinger distance is the probabilistic analog of euclidean distance comes from? why is that? $\endgroup$
    – carlo
    May 21, 2020 at 16:06

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.