Adversarially robust optimization with Gaussian processes
Name
NeurIPS-2018-adversarially-robust-optimization-with-gaussian-processes-Paper.pdf
Description
Published version
Size
3.12 MB
Format
Unknown
Checksum (MD5)
464ae61bffc8cc1cd564f91e68b5454f
Author(s)
Bogunovic, Ilija
Jegelka, Stefanie Sabrina
Scarlett, Jonathan
Cevher, Volkan
Date Issued
2018
Journal
Advances in Neural Information Processing Systems
Version
Final published version
Abstract
© 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 perturbation. This problem is motivated by settings in which the underlying functions during optimization and implementation stages are different, or when one is interested in finding an entire region of good inputs rather than only a single point. We show that standard GP optimization algorithms do not exhibit the desired robustness properties, and provide a novel confidence-bound based algorithm STABLEOPT for this purpose. We rigorously establish the required number of samples for STABLEOPT to find a near-optimal point, and we complement this guarantee with an algorithm-independent lower bound. We experimentally demonstrate several potential applications of interest using real-world data sets, and we show that STABLEOPT consistently succeeds in finding a stable maximizer where several baseline methods fail.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2018/hash/60243f9b1ac2dba11ff8131c8f4431e0-Abstract.html
