Sample-efficient Bayesian Optimisation Using Known Invariances

2 code implementations • 22 Oct 2024 • Theodore Brown, Alexandru Cioba, Ilija Bogunovic

We derive a bound on the maximum information gain of these invariant kernels, and provide novel upper and lower bounds on the number of observations required for invariance-aware BO algorithms to achieve $\epsilon$-optimality.

Bayesian Optimisation