Distributionally robust optimization and generalization in kernel methods M Staib, S Jegelka Advances in Neural Information Processing Systems 32, 2019 | 153 | 2019 |
Inorganic materials synthesis planning with literature-trained neural networks E Kim, Z Jensen, A van Grootel, K Huang, M Staib, S Mysore, HS Chang, ... Journal of chemical information and modeling 60 (3), 1194-1201, 2020 | 130 | 2020 |
Parallel streaming Wasserstein barycenters M Staib, S Claici, JM Solomon, S Jegelka Advances in Neural Information Processing Systems, 2647-2658, 2017 | 100 | 2017 |
Escaping saddle points with adaptive gradient methods M Staib, SJ Reddi, S Kale, S Kumar, S Sra Proceedings of the 36th International Conference on Machine Learning 97 …, 2019 | 93 | 2019 |
Distributionally robust deep learning as a generalization of adversarial training M Staib, S Jegelka NIPS workshop on Machine Learning and Computer Security 3, 4, 2017 | 80 | 2017 |
Robust Budget Allocation via Continuous Submodular Functions M Staib, S Jegelka Proceedings of the 34th International Conference on Machine Learning 70 …, 2017 | 59 | 2017 |
Distributionally robust submodular maximization M Staib, B Wilder, S Jegelka Proceedings of the Twenty-Second International Conference on Artificial …, 2019 | 38 | 2019 |
Sheshera Mysore, Haw-Shiuan Chang, Emma Strubell, Andrew McCallum, Stefanie Jegelka, et al E Kim, Z Jensen, A van Grootel, K Huang, M Staib Inorganic materials synthesis planning with literature-trained neural …, 2020 | 15 | 2020 |
Wasserstein k-means++ for cloud regime histogram clustering M Staib, S Jegelka Climate informatics, 2017 | 12 | 2017 |
Improving survey aggregation with sparsely represented signals T Shi, F Agostinelli, M Staib, D Wipf, T Moscibroda Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge …, 2016 | 3 | 2016 |
Learning and optimization in the face of data perturbations MJ Staib Massachusetts Institute of Technology, 2020 | 2 | 2020 |
1 Last Time-JL Lemma AM Scribe, R LaVigne, M Staib, D Tsipras | | |