Publications

In this paper, we propose to dynamically adjust particles’ weights according to a Fisher-Rao reaction flow. We develop a general Dynamic-weight Particle-based Variational Inference (DPVI) framework according to a novel continuous composite flow, which evolves the positions and weights of particles simultaneously.

Chao Zhang, Zhijian Li, Hui Qian, Xin Du

arXiv:2112.00945 (2021)

We propose a novel criterion to measure the graph matching accuracy, structural inconsistency (SI), which is defined based on the network topological structure.

Weijie Liu, Chao Zhang, Nenggan Zheng, Hui Qian

arXiv:2202.02797 (2022)

We propose the first theoretically guaranteed algorithms for general minimax problems in the cross-device federated learning setting.

Weijie Liu, Chao Zhang, Nenggan Zheng, Hui Qian

arXiv:2202.02797 (2022)

This paper presents a Hessian aided policy gradient method with the first improved sample complexity of $O ({1}/{\epsilon^ 3}) $.

Zebang Shen, Alejandro Ribeiro, Hamed Hassani, Hui Qian, Chao Mi

International conference on machine learning (2019)

We propose the first theoretically guaranteed algorithms for general minimax problems in the cross-device federated learning setting.

Jiahao Xie, Chao Zhang, Zebang Shen, Weijie Liu, Hui Qian

arXiv:2105.14216 (2021)