论文标题
Matérn内核RKH中功能的强盗优化
Bandit optimisation of functions in the Matérn kernel RKHS
论文作者
论文摘要
我们考虑了在域内$ [0,1]^d $上，在嘈杂的强盗反馈下，具有平滑度参数$ν$的零件内核的复制核Hilbert Space（RKHS）中优化功能的问题。我们的贡献是$π$ -GP-UCB算法，是第一种实用方法，保证了所有$ν> 1 $和$ d \ geq 1 $的Sublinear后悔。经验验证表明，与其前身改善的GP-UCB相比，相比，其性能更好，并大大提高了计算缩放性。
We consider the problem of optimising functions in the reproducing kernel Hilbert space (RKHS) of a Matérn kernel with smoothness 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 $d \geq 1$. Empirical validation suggests better performance and drastically improved computational scalablity compared with its predecessor, Improved GP-UCB.
