This topic has been introduced in "Pattern Recognition and Machine Learning, Bishop, 2006", section 5.4.1. I am a bit confused about this method and I have two questions.

  1. Why this method has attracted attention or has been developed? First, we want to compute the Hessian fast, so we try to approximate it in O(W) time, where W is the number of parameters. And then, we see that this matrix most of the time is heavily non-diagonal.

  2. My second question is how can we know whether we can approximate a Hessian or not? Is there a hint/clue in problems?

Thanks in advance!

  • $\begingroup$ Hello. Please, provide more context about this "Hessian Diagonal Approximation". Provide a link to or name of the paper/book/etc that describes this. Moreover, please, to improve the clarity of your post, put your specific question in the title. $\endgroup$
    – nbro
    Dec 19 '21 at 13:41
  • $\begingroup$ @nbro Thanks for the guidance. I did my best. I hope it is clear enough now. $\endgroup$ Dec 19 '21 at 13:52
  • $\begingroup$ Ok, thanks. I think your question is a duplicate of this. Let me know if I am correct. $\endgroup$
    – nbro
    Dec 19 '21 at 22:56

Your Answer

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

Browse other questions tagged or ask your own question.