no code implementations • 6 Mar 2024 • Anna P. Meyer, Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
Our empirical evaluation demonstrates that VeriTraCER generates CEs that (1) are verifiably robust to small model updates and (2) display competitive robustness to state-of-the-art approaches in handling empirical model updates including random initialization, leave-one-out, and distribution shifts.
no code implementations • 11 Jun 2023 • Anna P. Meyer, Dan Ley, Suraj Srinivas, Himabindu Lakkaraju
To this end, we conduct rigorous theoretical analysis to demonstrate that model curvature, weight decay parameters while training, and the magnitude of the dataset shift are key factors that determine the extent of explanation (in)stability.
1 code implementation • 20 Apr 2023 • Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
We introduce dataset multiplicity, a way to study how inaccuracies, uncertainty, and social bias in training datasets impact test-time predictions.
no code implementations • 7 Jun 2022 • Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets.
no code implementations • NeurIPS 2021 • Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
To certify robustness, we use a novel symbolic technique to evaluate a decision-tree learner on a large, or infinite, number of datasets, certifying that each and every dataset produces the same prediction for a specific test point.