1

I have a black box loss function that is evaluated by an external stimulator. It accepts two vectors $x$ and $y$ , $L(x,y)$. I have the freedom to choose $y$ for a given $x$. Therefore, I would like to pick $y$ that minimizes $L(x,y)$. If we model the mapping from $x$ to the optimal $y$ by a neural network producing $y=f(x)$, I would like to iteratively improve $f$ by a training process by evaluating $L$ as little as possible.

I am wondering what would be the best method to do this training.

I am aware of the cross-entropy method which improves by iteratively choosing the elites over the samples. I am wondering if there is any other method that I must consider before working on the implementation.

kjetil b halvorsen
  • 63,378
  • 26
  • 142
  • 467
Suresh
  • 143
  • 5
  • 1
    A related post -- The same problem general problem (black box optimization for an expensive function) is addressed here, albeit without the neural networks component. https://stats.stackexchange.com/questions/193306/optimization-when-cost-function-slow-to-evaluate/193310#193310 – Sycorax Mar 24 '21 at 16:12

0 Answers0