What is the particular reason for which we use sparse matrix X in dictionary learning equation Y=DX where Y is the signal matrix, D is dictionary and X is the coefficient matrix?

  • $\begingroup$ Since the dictionary is sparse. $\endgroup$ Mar 10, 2019 at 18:21
  • $\begingroup$ @YuvalFilmus No, the dictionary is not sparse. But the X matrix is sparse. $\endgroup$
    – Aleph
    Mar 10, 2019 at 18:25
  • $\begingroup$ Right, the dictionary used in a particular document is sparse, and we can use it to our advantage. $\endgroup$ Mar 10, 2019 at 18:26
  • 1
    $\begingroup$ Using sparsity, you can recover the dictionary from fewer samples. $\endgroup$ Mar 10, 2019 at 18:51
  • 1
    $\begingroup$ You can look up sparse dictionary learning and compressed sensing on Wikipedia. $\endgroup$ Mar 10, 2019 at 18:53


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.