5
$\begingroup$

In this paper related to factorization machine, the author compares factorization machine (FM) with SVM. As FM performs better than SVM, it's considered state of the art for sparse data. Why SVM is considered so important algorithm for sparse dataset? What features of SVM makes it superior for sparse data?

$\endgroup$
1
  • $\begingroup$ I think this could be a good question if you added some more detail and if you could narrow down your question :) $\endgroup$
    – oW_
    Aug 10 '17 at 22:12
8
$\begingroup$

Support Vector Machines (SVM) represent data examples as points in space and tries to create a mapping with a wide as possible gap between the separate categories. The data examples closest to the gap are called "support vectors". Those support vectors define the SVM classifier.

If you are able to identify the support vectors, you can ignore all other data points and dimensions. Thus SVM can efficiently handle sparse data.

$\endgroup$
2
  • $\begingroup$ The answer makes no sense. How can you ignore dimensions when identifying a point in space? $\endgroup$
    – sandyp
    Aug 2 '18 at 16:03
  • 1
    $\begingroup$ If the matrix is not full rank, dimensions are a linear combination of other dimensions. Those dimensions can be ignored because the information of those features are modeled by the other dimensions. $\endgroup$ Aug 2 '18 at 16:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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