0
$\begingroup$

I have a set of items S. items can be joined to groups consisting of up to x items. For a group of items i can derive a score Y using some unknown performance measure. What would be the most efficient way to find the "best" performing group without doing an exhaustive search, that is, try all possible combinations? Would this be a candidate for a simple genetic algorithm?

Thanks

| cite | improve this question | |
$\endgroup$
  • $\begingroup$ Is this related to your other question stats.stackexchange.com/questions/128864 ? $\endgroup$ – Juho Kokkala Dec 17 '14 at 13:27
  • $\begingroup$ If it is an arbitrary score function you cannot. If it has some concave structure, I believe it can be very efficiently implemented with a LASSO penalty without doing exhaustive search. $\endgroup$ – Cagdas Ozgenc Dec 17 '14 at 13:31
1
$\begingroup$

If you known nothing about your performance measure, then no free lunch theorem seems to imply that you can't expect to improve the performance of exhaustive search.

| cite | improve this answer | |
$\endgroup$

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.