Towards the unification and robustness of perturbation and gradient based explanations S Agarwal, S Jabbari, C Agarwal, S Upadhyay, S Wu, H Lakkaraju International Conference on Machine Learning, 110-119, 2021 | 53 | 2021 |
Trade-offs between fairness and privacy in machine learning S Agarwal IJCAI 2021 Workshop on AI for Social Good, 2021 | 28 | 2021 |
On Trade-Offs between Fairness, Interpretability, and Privacy in Classification S Agarwal University of Waterloo, 2020 | 21* | 2020 |
On Learnability with Computable Learners S Agarwal, N Ananthakrishnan, S Ben-David, T Lechner, R Urner Algorithmic Learning Theory, 48-60, 2020 | 20 | 2020 |
Trade-offs between fairness and interpretability in machine learning S Agarwal IJCAI 2021 Workshop on AI for Social Good, 1-6, 2021 | 19 | 2021 |
Impossibility Results for Fair Representations T Lechner, S Ben-David, S Agarwal, N Ananthakrishnan arXiv preprint arXiv:2107.03483, 2021 | 13 | 2021 |
On the Power of Randomization in Fair Classification and Representation S Agarwal, A Deshpande 2022 ACM Conference on Fairness, Accountability, and Transparency, 1542-1551, 2022 | 7 | 2022 |
Open Problem: Are all VC-classes CPAC Learnable? S Agarwal, N Ananthakrishnan, S Ben-David, T Lechner, R Urner Conference on Learning Theory, 4636-4641, 2021 | 6 | 2021 |
Private Mean Estimation with Person-Level Differential Privacy S Agarwal, G Kamath, M Majid, A Mouzakis, R Silver, J Ullman arXiv preprint arXiv:2405.20405, 2024 | | 2024 |