no code implementations • 5 Jan 2022 • Ningyuan Chen, Shuoguang Yang, Hailun Zhang
In the multi-armed bandit framework, there are two formulations that are commonly employed to handle time-varying reward distributions: adversarial bandit and nonstationary bandit.
no code implementations • 16 Sep 2021 • Minghao Gao, Hailun Zhang, Yige Yan
Knowledge distillation methods are proved to be promising in improving the performance of neural networks and no additional computational expenses are required during the inference time.
1 code implementation • 6 Sep 2020 • Yuhao Zhou, Qing Ye, Hailun Zhang, Jiancheng Lv
While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming data synchronizing between workers.