Adversarially robust optimization with Gaussian processes

© 2018 Curran Associates Inc.All rights reserved. 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 pe...

Full description

Bibliographic Details
Main Authors: Bogunovic, I, Jegelka, S, Scarlett, J, Cevher, V
Format: Article
Language:English
Published: 2021
Online Access:https://hdl.handle.net/1721.1/132304