Distributed Ranking with Communications: Approximation Analysis and Applications

Abstract

Learning theory of distributed algorithms has recently attracted enormous attention in the machine learning community. However, most of existing works focus on learning problem with pointwise loss and does not consider the communication among local processors. In this paper, we propose a new distributed pairwise ranking with communication (called DLSRank-C) based on the Newton-Raphson iteration, and establish its learning rate analysis in probability. Theoretical and empirical assessments demonstrate the effectiveness of DLSRank-C under mild conditions.

Cite

Text

Chen et al. "Distributed Ranking with Communications: Approximation Analysis and Applications." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I8.16866

Markdown

[Chen et al. "Distributed Ranking with Communications: Approximation Analysis and Applications." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/chen2021aaai-distributed/) doi:10.1609/AAAI.V35I8.16866

BibTeX

@inproceedings{chen2021aaai-distributed,
  title     = {{Distributed Ranking with Communications: Approximation Analysis and Applications}},
  author    = {Chen, Hong and Wang, Yingjie and Wang, Yulong and Zheng, Feng},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {7037-7045},
  doi       = {10.1609/AAAI.V35I8.16866},
  url       = {https://mlanthology.org/aaai/2021/chen2021aaai-distributed/}
}