| Multitask learning and bandits via robust statistics K Xu, H Bastani Available at SSRN 4779711, 2024 | 18* | 2024 |
| Safely bridging offline and online reinforcement learning W Xu, K Xu, H Bastani, O Bastani arXiv preprint arXiv:2110.13060, 2021 | 11 | 2021 |
| Group-sparse matrix factorization for transfer learning of word embeddings K Xu, X Zhao, H Bastani, O Bastani International Conference on Machine Learning, 11603-11612, 2021 | 7 | 2021 |
| Robust generalization of quadratic neural networks via function identification K Xu, H Bastani, O Bastani arXiv preprint arXiv:2109.10935, 2021 | 6 | 2021 |
| Uniformly conservative exploration in reinforcement learning W Xu, Y Ma, K Xu, H Bastani, O Bastani International Conference on Artificial Intelligence and Statistics, 10856-10870, 2023 | 5 | 2023 |
| Two-stage maximum score estimator WY Gao, S Xu, K Xu arXiv preprint arXiv:2009.02854, 2020 | 4 | 2020 |
| Stochastic Bandits with ReLU Neural Networks K Xu, H Bastani, S Goel, O Bastani arXiv preprint arXiv:2405.07331, 2024 | | 2024 |
| Essays on novel data-driven decision making methods K Xu University of Pennsylvania, 2023 | | 2023 |
Hamsa BastaniAssociate Professor of Operations Information and Decisions, Wharton SchoolBestätigte E-Mail-Adresse bei wharton.upenn.edu
