Hm. Is the noise magnitude comparable with features in your search space? In other words, can you ignore noise to get a fast lock on a promising section of the space and then start multiple sampling?
Simulated annealing that has been mentioned is a good approach but slow to the extent of being impractical for large search spaces.
Solutions to problems such as yours are rarely general and typically depend on the specifics of the problem—essentially it’s all about finding shortcuts.
The parameter space in this current problem is only two dimensional, so I can eyeball a plausible region, sample at a higher rate there, and iterate by hand. In another project, I had something with an very high dimensional parameter space, so I figured it’s time I learn more about these techniques.
Any resources you can recommend on this topic then? Is there a list of common shortcuts anywhere?
Hm. Is the noise magnitude comparable with features in your search space? In other words, can you ignore noise to get a fast lock on a promising section of the space and then start multiple sampling?
Simulated annealing that has been mentioned is a good approach but slow to the extent of being impractical for large search spaces.
Solutions to problems such as yours are rarely general and typically depend on the specifics of the problem—essentially it’s all about finding shortcuts.
The parameter space in this current problem is only two dimensional, so I can eyeball a plausible region, sample at a higher rate there, and iterate by hand. In another project, I had something with an very high dimensional parameter space, so I figured it’s time I learn more about these techniques.
Any resources you can recommend on this topic then? Is there a list of common shortcuts anywhere?
Well, optimization (aka search in parameter space) is a large and popular topic. There are a LOT of papers and books about it.
And sorry, I don’t know of a list of common shortcuts. As I mentioned they really depend on the specifics of the problem.