Adversarial training can hurt generalization A Raghunathan, SM Xie, F Yang, JC Duchi, P Liang arXiv preprint arXiv:1906.06032, 2019 | 277 | 2019 |
Understanding and mitigating the tradeoff between robustness and accuracy A Raghunathan, SM Xie, F Yang, J Duchi, P Liang arXiv preprint arXiv:2002.10716, 2020 | 259 | 2020 |
Regularized learning for domain adaptation under label shifts K Azizzadenesheli, A Liu, F Yang, A Anandkumar arXiv preprint arXiv:1903.09734, 2019 | 228 | 2019 |
Early stopping for kernel boosting algorithms: A general analysis with localized complexities Y Wei, F Yang, MJ Wainwright Advances in Neural Information Processing Systems 30, 2017 | 92 | 2017 |
A framework for multi-a (rmed)/b (andit) testing with online fdr control F Yang, A Ramdas, KG Jamieson, MJ Wainwright Advances in Neural Information Processing Systems 30, 2017 | 76 | 2017 |
Online control of the false discovery rate with decaying memory A Ramdas, F Yang, MJ Wainwright, MI Jordan Advances in neural information processing systems 30, 2017 | 73 | 2017 |
Statistical and computational guarantees for the Baum-Welch algorithm F Yang, S Balakrishnan, MJ Wainwright Journal of Machine Learning Research 18 (125), 1-53, 2017 | 71 | 2017 |
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness F Yang, Z Wang, C Heinze-Deml Advances in neural information processing systems 32, 2019 | 44 | 2019 |
Tight bounds for minimum -norm interpolation of noisy data G Wang, K Donhauser, F Yang International Conference on Artificial Intelligence and Statistics, 10572-10602, 2022 | 38 | 2022 |
Phaseless signal recovery in infinite dimensional spaces using structured modulations V Pohl, F Yang, H Boche Journal of Fourier Analysis and Applications 20, 1212-1233, 2014 | 38 | 2014 |
How unfair is private learning? A Sanyal, Y Hu, F Yang Uncertainty in Artificial Intelligence, 1738-1748, 2022 | 28 | 2022 |
How rotational invariance of common kernels prevents generalization in high dimensions K Donhauser, M Wu, F Yang International Conference on Machine Learning, 2804-2814, 2021 | 26 | 2021 |
Fast rates for noisy interpolation require rethinking the effect of inductive bias K Donhauser, N Ruggeri, S Stojanovic, F Yang International Conference on Machine Learning, 5397-5428, 2022 | 25 | 2022 |
Phase retrieval via structured modulations in Paley-Wiener spaces F Yang, V Pohl, H Boche arXiv preprint arXiv:1302.4258, 2013 | 22 | 2013 |
Self-supervised reinforcement learning with independently controllable subgoals A Zadaianchuk, G Martius, F Yang Conference on Robot Learning, 384-394, 2022 | 21 | 2022 |
Phase retrieval from low-rate samples V Pohl, H Boche, F Yang Sampling Theory in Signal and Image Processing 14, 71-99, 2015 | 21 | 2015 |
Semi-supervised novelty detection using ensembles with regularized disagreement A Tifrea, E Stavarache, F Yang Uncertainty in Artificial Intelligence, 1939-1948, 2022 | 16 | 2022 |
Why adversarial training can hurt robust accuracy J Clarysse, J Hörrmann, F Yang arXiv preprint arXiv:2203.02006, 2022 | 16 | 2022 |
Margin-based sampling in high dimensions: When being active is less efficient than staying passive A Tifrea, J Clarysse, F Yang International Conference on Machine Learning, 34222-34262, 2023 | 14* | 2023 |
Interpolation can hurt robust generalization even when there is no noise K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang Advances in Neural Information Processing Systems 34, 23465-23477, 2021 | 14 | 2021 |