no code implementations • 28 Sep 2022 • Shai Feldman, Bat-Sheva Einbinder, Stephen Bates, Anastasios N. Angelopoulos, Asaf Gendler, Yaniv Romano
In such cases, we can also correct for noise of bounded size in the conformal prediction algorithm in order to ensure achieving the correct risk of the ground truth labels without score or data regularity.
no code implementations • ICLR 2022 • Asaf Gendler, Tsui-Wei Weng, Luca Daniel, Yaniv Romano
By combining conformal prediction with randomized smoothing, our proposed method forms a prediction set with finite-sample coverage guarantee that holds for any data distribution with $\ell_2$-norm bounded adversarial noise, generated by any adversarial attack algorithm.