Densely connected convolutional networks with attention LSTM for crowd flows prediction W Li, W Tao, J Qiu, X Liu, X Zhou, Z Pan IEEE Access 7, 140488-140498, 2019 | 39 | 2019 |
Primal averaging: A new gradient evaluation step to attain the optimal individual convergence W Tao, Z Pan, G Wu, Q Tao IEEE Transactions on Cybernetics 50 (2), 835-845, 2018 | 23 | 2018 |
The strength of Nesterov’s extrapolation in the individual convergence of nonsmooth optimization W Tao, Z Pan, G Wu, Q Tao IEEE Transactions on Neural Networks and Learning Systems 31 (7), 2557-2568, 2019 | 22 | 2019 |
The role of momentum parameters in the optimal convergence of adaptive Polyak's heavy-ball methods W Tao, S Long, G Wu, Q Tao arXiv preprint arXiv:2102.07314, 2021 | 19 | 2021 |
Regularized shapelet learning for scalable time series classification H Zhao, Z Pan, W Tao Computer Networks 173, 107171, 2020 | 15 | 2020 |
Momentum acceleration in the individual convergence of nonsmooth convex optimization with constraints W Tao, G Wu, Q Tao IEEE Transactions on Neural Networks and Learning Systems, 2020 | 11 | 2020 |
Provable convergence of nesterov’s accelerated gradient method for over-parameterized neural networks X Liu, Z Pan, W Tao Knowledge-Based Systems 251, 109277, 2022 | 9 | 2022 |
使用Nesterov步长策略投影次梯度方法的个体收敛性 陶蔚, 潘志松, 储德军, 陶卿 计算机学报 41 (1), 164-176, 2018 | 8 | 2018 |
A convergence analysis of Nesterov’s accelerated gradient method in training deep linear neural networks X Liu, W Tao, Z Pan Information Sciences 612, 898-925, 2022 | 5 | 2022 |
Heavy-Ball 型动量方法的最优个体收敛速率 程禹嘉, 陶蔚, 刘宇翔, 陶卿 计算机研究与发展 56 (8), 1686-1694, 2019 | 4 | 2019 |
A high-resolution dynamical view on momentum methods for over-parameterized neural networks X Liu, W Tao, J Wang, Z Pan arXiv preprint arXiv:2208.03941, 2022 | 3 | 2022 |
A unified momentum method with triple-parameters and its optimal convergence rate CC Ding, W Tao, Q Tao Journal of computer research and development 57, 1571-1580, 2020 | 3 | 2020 |
Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization W Tao, W Li, Z Pan, Q Tao In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI …, 2020 | 2 | 2020 |
Token-level disentanglement for unsupervised text style transfer Y Hu, W Tao, Y Xie, Y Sun, Z Pan Neurocomputing 560, 126823, 2023 | 1 | 2023 |
Location and time embedded feature representation for spatiotemporal traffic prediction W Li, X Liu, W Tao, L Zhang, J Zou, Y Pan, Z Pan Expert Systems with Applications, 122449, 2023 | 1 | 2023 |
Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks W Tao, L Bao, S Long, G Wu, Q Tao arXiv preprint arXiv:2301.11546, 2023 | 1 | 2023 |
非光滑强凸情形 Adam 型算法的最优收敛速率 陇盛, 陶蔚, 张泽东, 陶卿 电子学报 50 (9), 2049-2059, 2022 | 1 | 2022 |
Tolerance-oriented wi-fi advertisement scheduling: A near optimal study on accumulative user interests W Xu, X Fan, T Wu, W Tao, Y Xi, P Yang, C Tian Mobile Networks and Applications 26 (6), 2242-2257, 2021 | 1 | 2021 |
Adaptive NAG Methods Based on AdaGrad and Its Optimal Individual Convergence Journal of Software 33 (4), 1231-1243, 2021 | 1* | 2021 |
On the Convergence of an Adaptive Momentum Method for Adversarial Attacks S Long, W Tao, LI Shuohao, J Lei, J Zhang Proceedings of the AAAI Conference on Artificial Intelligence 38 (13), 14132 …, 2024 | | 2024 |