Piecewise linear activations substantially shape the loss surfaces of neural networks F He*, B Wang*, D Tao International Conference on Learning Representations (ICLR) 2020, 2020 | 25 | 2020 |
Machine-learning nonconservative dynamics for new-physics detection Z Liu, B Wang, Q Meng, W Chen, M Tegmark, TY Liu Physical Review E 104 (5), 055302, 2021 | 16 | 2021 |
Tighter generalization bounds for iterative differentially private learning algorithms F He*, B Wang*, D Tao Uncertainty in Artificial Intelligence (UAI) 2021, 2021 | 15 | 2021 |
The implicit bias for adaptive optimization algorithms on homogeneous neural networks B Wang, Q Meng, W Chen, TY Liu International Conference on Machine Learning, 10849-10858, 2021 | 14 | 2021 |
Creating training sets via weak indirect supervision J Zhang, B Wang, X Song, Y Wang, Y Yang, J Bai, A Ratner ICLR 2022, 0 | 9* | |
Robustness, privacy, and generalization of adversarial training F He, S Fu, B Wang, D Tao arXiv preprint arXiv:2012.13573, 2020 | 7 | 2020 |
Provable Adaptivity in Adam B Wang, Y Zhang, H Zhang, Q Meng, ZM Ma, TY Liu, W Chen arXiv preprint arXiv:2208.09900, 2022 | 5 | 2022 |
Does Momentum Change the Implicit Regularization on Separable Data? B Wang, Q Meng, H Zhang, R Sun, W Chen, ZM Ma Neurips 2022, 0 | 5* | |
Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD B Wang, H Zhang, J Zhang, Q Meng, W Chen, TY Liu 35th Conference on Neural Information Processing Systems (Neurips 2021), 2021 | 4 | 2021 |