no code implementations • 17 Mar 2024 • Xuetong Li, Yuan Gao, Hong Chang, Danyang Huang, Yingying Ma, Rui Pan, Haobo Qi, Feifei Wang, Shuyuan Wu, Ke Xu, Jing Zhou, Xuening Zhu, Yingqiu Zhu, Hansheng Wang
A huge amount of statistical methods for massive data computation have been rapidly developed in the past decades.
no code implementations • 7 Jun 2023 • Shuyuan Wu, Danyang Huang, Hansheng Wang
This considerably reduces the computation and communication complexity of the proposed method.
no code implementations • 13 Apr 2023 • Qianhan Zeng, Yingqiu Zhu, Xuening Zhu, Feifei Wang, Weichen Zhao, Shuning Sun, Meng Su, Hansheng Wang
Labeling mistakes are frequently encountered in real-world applications.
no code implementations • 23 Nov 2022 • Jing Zhou, Xinru Jing, Muyu Liu, Hansheng Wang
This leads to a benchmark model, which we then use to obtain the predicted class probabilities for each sample in a dataset.
no code implementations • 6 May 2022 • Shuyuan Wu, Danyang Huang, Hansheng Wang
The resulting NGD estimator can be statistically as efficient as the global estimator, if the learning rate is sufficiently small and the network structure is well balanced, even if the data are distributed heterogeneously.
1 code implementation • 1 Jan 2021 • Haobo Qi, Jing Zhou, Hansheng Wang
Deep neural network (DNN) models often involve features of ultrahigh dimensions.
no code implementations • 2 Jun 2020 • Yingying Ma, Hansheng Wang
In this article we develop a hyperparameter selection methodology, which can be used to select tuning parameters for subsampling methods.
1 code implementation • 7 Apr 2020 • Yingqiu Zhu, Yu Chen, Danyang Huang, Bo Zhang, Hansheng Wang
In each update step, given the gradient direction, we locally approximate the loss function by a standard quadratic function of the learning rate.
2 code implementations • 14 Aug 2019 • Xuening Zhu, Feng Li, Hansheng Wang
The finite sample performance and computational efficiency are further illustrated by an extensive numerical study and an airline dataset.