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.
1 code implementation • 18 May 2022 • Shai Feldman, Liran Ringel, Stephen Bates, Yaniv Romano
To provide rigorous uncertainty quantification for online learning models, we develop a framework for constructing uncertainty sets that provably control risk -- such as coverage of confidence intervals, false negative rate, or F1 score -- in the online setting.
1 code implementation • 31 Jan 2022 • Or Feldman, Amit Boyarski, Shai Feldman, Dani Kogan, Avi Mendelson, Chaim Baskin
Two popular alternatives that offer a good trade-off between expressive power and computational efficiency are combinatorial (i. e., obtained via the Weisfeiler-Leman (WL) test) and spectral invariants.
1 code implementation • 2 Oct 2021 • Shai Feldman, Stephen Bates, Yaniv Romano
We develop a method to generate predictive regions that cover a multivariate response variable with a user-specified probability.
1 code implementation • NeurIPS 2021 • Shai Feldman, Stephen Bates, Yaniv Romano
To remedy this, we modify the loss function to promote independence between the size of the intervals and the indicator of a miscoverage event.