| The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects Z Zhu, J Wu, B Yu, L Wu, J Ma International Conference on Machine Learning, 7654-7663, 2019 | 339* | 2019 |
| On the Noisy Gradient Descent that Generalizes as SGD J Wu, W Hu, H Xiong, J Huan, V Braverman, Z Zhu International Conference on Machine Learning, 10367-10376, 2020 | 140 | 2020 |
| Programmable packet scheduling with a single queue Z Yu, C Hu, J Wu, X Sun, V Braverman, M Chowdhury, Z Liu, X Jin Proceedings of the 2021 ACM SIGCOMM 2021 Conference, 179-193, 2021 | 133 | 2021 |
| How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? J Wu, D Zou, Z Chen, V Braverman, Q Gu, PL Bartlett arXiv preprint arXiv:2310.08391, 2023 | 108 | 2023 |
| Benign overfitting of constant-stepsize SGD for linear regression D Zou, J Wu, V Braverman, Q Gu, SM Kakade Journal of Machine Learning Research 24 (326), 1-58, 2023 | 108 | 2023 |
| Twenty years after: Hierarchical {Core-Stateless} fair queueing Z Yu, J Wu, V Braverman, I Stoica, X Jin 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI …, 2021 | 60 | 2021 |
| The benefits of implicit regularization from sgd in least squares problems D Zou, J Wu, V Braverman, Q Gu, DP Foster, S Kakade Advances in neural information processing systems 34, 5456-5468, 2021 | 51 | 2021 |
| A collective AI via lifelong learning and sharing at the edge A Soltoggio, E Ben-Iwhiwhu, V Braverman, E Eaton, B Epstein, Y Ge, ... Nature Machine Intelligence 6 (3), 251-264, 2024 | 50 | 2024 |
| Direction matters: On the implicit bias of stochastic gradient descent with moderate learning rate J Wu, D Zou, V Braverman, Q Gu International Conference on Learning Representations, 2021 | 48 | 2021 |
| Scaling laws in linear regression: Compute, parameters, and data L Lin, J Wu, SM Kakade, PL Bartlett, JD Lee arXiv preprint arXiv:2406.08466, 2024 | 44 | 2024 |
| Implicit bias of gradient descent for logistic regression at the edge of stability J Wu, V Braverman, JD Lee Advances in Neural Information Processing Systems 36, 74229-74256, 2023 | 42 | 2023 |
| Last iterate risk bounds of sgd with decaying stepsize for overparameterized linear regression J Wu, D Zou, V Braverman, Q Gu, S Kakade International conference on machine learning, 24280-24314, 2022 | 42 | 2022 |
| Tangent-normal adversarial regularization for semi-supervised learning B Yu, J Wu, J Ma, Z Zhu Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 39 | 2019 |
| Ship compute or ship data? why not both? J You, J Wu, X Jin, M Chowdhury 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI …, 2021 | 38 | 2021 |
| Fixed design analysis of regularization-based continual learning H Li, J Wu, V Braverman Conference on lifelong learning agents, 513-533, 2023 | 33 | 2023 |
| Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency J Wu, PL Bartlett, M Telgarsky, B Yu The Thirty Seventh Annual Conference on Learning Theory, 5019-5073, 2024 | 32 | 2024 |
| In-context learning of a linear transformer block: Benefits of the mlp component and one-step gd initialization R Zhang, J Wu, P Bartlett Advances in Neural Information Processing Systems 37, 18310-18361, 2024 | 31 | 2024 |
| The power and limitation of pretraining-finetuning for linear regression under covariate shift J Wu, D Zou, V Braverman, Q Gu, S Kakade Advances in Neural Information Processing Systems 35, 33041-33053, 2022 | 31 | 2022 |
| How Does Critical Batch Size Scale in Pre-training? H Zhang, D Morwani, N Vyas, J Wu, D Zou, U Ghai, D Foster, S Kakade arXiv preprint arXiv:2410.21676, 2024 | 27 | 2024 |
| Large stepsize gradient descent for non-homogeneous two-layer networks: Margin improvement and fast optimization Y Cai, J Wu, S Mei, M Lindsey, P Bartlett Advances in Neural Information Processing Systems 37, 71306-71351, 2024 | 21 | 2024 |
Vladimir BravermanProfessor of Computer Science, Johns Hopkins University; Google Research; Adjunct Professor, Rice U.Verified email at cs.jhu.edu
