1
$\begingroup$

Convex optimisation is defined as:

enter image description here

I have seen a lot of talk about convex loss functions in Neural Networks and how we are optimising rewards or penalty in AI/ML systems. But I have never seen any loss function formulated in the aforementioned way. So my question is:

Is there any role of convex optimization in AI? If so, in what algorithms or problem settings or systems?

$\endgroup$
1
$\begingroup$

Is there any role of convex optimization in AI?

Yes, of course!

If so, in what algorithms or problem settings or systems?

The problem of finding the parameters of a support vector machine can be formulated as a convex optimization problem. Another example is linear regression.

See also the paper Convex Optimization: Algorithms and Complexity (2014) by Sébastien Bubeck, which also mentions SVM as a typical example.

| improve this answer | |
$\endgroup$
  • $\begingroup$ I'll accept the answer after I do a bit of my own research. $\endgroup$ – DuttaA Apr 3 at 21:03
  • $\begingroup$ @DuttaA Yes, don't worry. The first thing that came to mind when I read your question was SVM (because I am familiar enough with its details and I used it in the past). Anyway, I only skimmed through the first paragraphs of the paper I am linking to, but it looks like a paper that goes into the direction of your question. $\endgroup$ – nbro Apr 3 at 21:05

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.