← Search

Miklós Z. Horváth

2 accepted papers

2022

(De-)Randomized Smoothing for Decision Stump Ensembles

NeurIPS 2022accept

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. Ta…

2022

Boosting Randomized Smoothing with Variance Reduced Classifiers

ICLR 2022spotlight

Randomized Smoothing (RS) is a promising method for obtaining robustness certificates by evaluating a base model under noise. In this work, we: (i) theoretically motivate why ensembles are a particularly suitable choice as base models for RS, and (ii) empirically confirm this choice, obtaining state-o…