search

avaneev / biteopt

Derivative-Free Global Optimization Algorithm (C++, Python binding) - Continuous, Discrete, TSP, NLS, MINLP
MIT License
141 stars 9 forks source link

Benchmarking #3

Closed microprediction closed 2 years ago

microprediction commented 2 years ago

Hello, I maintain the humpday package which I use to select optimizers. Biteopt was brought to my attention by this issue and I'd like to include it. It seems like the other benchmarking has gone very well.

I'm assuming I can use biteopt? You say there are zero hyper-parameters, which is good, but is there anything obvious I should know? -Peter

avaneev commented 2 years ago

Hello! Yes, of course you can use biteopt as you wish, it's MIT licensed. I've made it as "plug and play" as possible, so there are no catches to my knowledge. I suggest you to take a look here: https://github.com/dietmarwo/fast-cma-es This implementation can use multiple threads (parallel retry). May be more practical considering BiteOpt by design requires several retries/attempts for complex problems.