Corruption-Tolerant Gaussian Process Bandit Optimization
AISTATS, pp. 1071-1081, 2020.
We consider the problem of optimizing an unknown (typically non-convex) function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit feedback. We consider a novel variant of this problem in which the point evaluations are not only corrupted by random noise, but also adversarial corruptions. We intr...More
PPT (Upload PPT)