Bridging Adversarial and Nonstationary Multi-armed Bandit

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.

Label Assignment Distillation for Object Detection

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.

Knowledge Distillation Object +2

HPSGD: Hierarchical Parallel SGD With Stale Gradients Featuring

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.