all AI news
General Cutting Planes for Bound-Propagation-Based Neural Network Verification. (arXiv:2208.05740v1 [cs.LG])
Aug. 12, 2022, 1:10 a.m. | Huan Zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter
cs.LG updates on arXiv.org arxiv.org
Bound propagation methods, when combined with branch and bound, are among the
most effective methods to formally verify properties of deep neural networks
such as correctness, robustness, and safety. However, existing works cannot
handle the general form of cutting plane constraints widely accepted in
traditional solvers, which are crucial for strengthening verifiers with
tightened convex relaxations. In this paper, we generalize the bound
propagation procedure to allow the addition of arbitrary cutting plane
constraints, including those involving relaxed integer variables …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Engineer
@ Quantexa | Sydney, New South Wales, Australia
Staff Analytics Engineer
@ Warner Bros. Discovery | NY New York 230 Park Avenue South