(De-)Randomized Smoothing for Decision Stump Ensembles. (arXiv:2205.13909v1 [cs.LG])

Tree-based models are used in many high-stakes application domains such as
finance and medicine, where robustness and interpretability are of utmost
importance. Yet, methods for improving and certifying their robustness are
severely under-explored, in contrast to those focusing on neural networks.
Targeting this important challenge, we propose deterministic smoothing for
decision stump ensembles. Whereas most prior work on randomized smoothing
focuses on evaluating arbitrary base models approximately under input
randomization, the key insight of our work is that decision stump …

decision lg