Dash: Semi-supervised learning with dynamic thresholding Y Xu, L Shang, J Ye, Q Qian, YF Li, B Sun, H Li, R Jin
International conference on machine learning, 11525-11536, 2021
277 2021 First-order stochastic algorithms for escaping from saddle points in almost linear time Y Xu, R Jin, T Yang
Advances in Neural Information Processing Systems, 5530-5540, 2018
145 2018 Chex: Channel exploration for cnn model compression Z Hou, M Qin, F Sun, X Ma, K Yuan, Y Xu, YK Chen, R Jin, Y Xie, SY Kung
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
92 2022 Self-supervised pre-training for transformer-based person re-identification H Luo, P Wang, Y Xu, F Ding, Y Zhou, F Wang, H Li, R Jin
arXiv preprint arXiv:2111.12084, 2021
81 2021 Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization Y Yan, Y Xu, Q Lin, W Liu, T Yang
Advances in Neural Information Processing Systems 33, 5789-5800, 2020
81 * 2020 Practical and theoretical considerations in study design for detecting gene-gene interactions using MDR and GMDR approaches GB Chen, Y Xu, HM Xu, MD Li, J Zhu, XY Lou
PloS one 6 (2), e16981, 2011
76 2011 ADMM without a fixed penalty parameter: Faster convergence with new adaptive penalization Y Xu, M Liu, Q Lin, T Yang
Advances in neural information processing systems 30, 2017
63 2017 On stochastic moving-average estimators for non-convex optimization Z Guo, Y Xu, W Yin, R Jin, T Yang
arXiv preprint arXiv:2104.14840, 2021
61 2021 Stochastic convex optimization: Faster local growth implies faster global convergence Y Xu, Q Lin, T Yang
International Conference on Machine Learning, 3821-3830, 2017
53 2017 A novel convergence analysis for algorithms of the adam family Z Guo, Y Xu, W Yin, R Jin, T Yang
arXiv preprint arXiv:2112.03459, 2021
51 2021 Towards understanding label smoothing Y Xu, Y Xu, Q Qian, H Li, R Jin
arXiv preprint arXiv:2006.11653, 2020
48 2020 Stochastic optimization for DC functions and non-smooth non-convex regularizers with non-asymptotic convergence Y Xu, Q Qi, Q Lin, R Jin, T Yang
International conference on machine learning, 6942-6951, 2019
48 2019 Improved fine-tuning by better leveraging pre-training data Z Liu, Y Xu, Y Xu, Q Qian, H Li, X Ji, A Chan, R Jin
Advances in Neural Information Processing Systems 35, 32568-32581, 2022
47 * 2022 An online method for a class of distributionally robust optimization with non-convex objectives Q Qi, Z Guo, Y Xu, R Jin, T Yang
Advances in Neural Information Processing Systems 34, 2021
41 2021 Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity Z Yuan, Z Guo, Y Xu, Y Ying, T Yang
International Conference on Machine Learning, 12219-12229, 2021
39 2021 Effective model sparsification by scheduled grow-and-prune methods X Ma, M Qin, F Sun, Z Hou, K Yuan, Y Xu, Y Wang, YK Chen, R Jin, Y Xie
arXiv preprint arXiv:2106.09857, 2021
38 2021 Sadagrad: Strongly adaptive stochastic gradient methods Z Chen*, Y Xu*, E Chen, T Yang
International Conference on Machine Learning, 913-921, 2018
36 2018 Stochastic Primal-Dual Algorithms with Faster Convergence than Y Yan, Y Xu, Q Lin, L Zhang, T Yang
arXiv preprint arXiv:1904.10112, 2019
33 2019 Non-asymptotic analysis of stochastic methods for non-smooth non-convex regularized problems Y Xu, R Jin, T Yang
Advances In Neural Information Processing Systems 32, 2630-2640, 2019
32 * 2019 Learning with non-convex truncated losses by SGD Y Xu, S Zhu, S Yang, C Zhang, R Jin, T Yang
Uncertainty in Artificial Intelligence, 701-711, 2020
29 2020 
Tianbao YangTexas A&M UniversityAdresse e-mail validée de tamu.edu
