secondmind-labs / trieste

A Bayesian optimization toolbox built on TensorFlow
Apache License 2.0
212 stars 42 forks source link

Multi-objective optimization with Expected HyperVolume Improvement #803

Open Mairafatoretto opened 7 months ago

Mairafatoretto commented 7 months ago

In this example are you find the maximum of the functions? Where i need chance to get the minimization?

satrialoka commented 6 months ago

It is already minimization, see note. For a naive way to switch between minimization/maximization, you can write a custom observer, by multiplying your objective(s) by -1