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.
Neural Information Processing Systems
Nov-20-2025, 16:48:55 GMT
- Country:
- Asia > Singapore (0.04)
- North America
- United States > Massachusetts
- Middlesex County > Cambridge (0.04)
- Canada > Quebec
- Montreal (0.04)
- United States > Massachusetts
- Europe > Switzerland
- Technology: