Bandit optimisation of functions in the Matérn kernel RKHS

01/28/2020
by   David Janz, et al.
0

We consider the problem of optimising functions in the Reproducing kernel Hilbert space (RKHS) of a Matérn family kernel with parameter ν over the domain [0,1]^d under noisy bandit feedback. Our contribution, the π-GP-UCB algorithm, is the first practical approach with guaranteed sublinear regret for all ν>1 and d ≥ 1. Empirical validation suggests better performance and drastically improved computational scalablity compared with its predecessor, Improved GP-UCB.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset