Adversarially Robust Optimization with Gaussian Processes

Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher

Neural Information Processing Systems 

In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturbation.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found