Distributed Ranking with Communications: Approximation Analysis and Applications

Authors

  • Hong Chen Huazhong Agricultural University, China
  • Yingjie Wang Huazhong Agricultural University, China
  • Yulong Wang Huazhong Agricultural University, China
  • Feng Zheng Southern University of Science and Technology, China

Keywords:

Learning Theory

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.

Downloads

Published

2021-05-18

How to Cite

Chen, H., Wang, Y., Wang, Y., & Zheng, F. (2021). Distributed Ranking with Communications: Approximation Analysis and Applications. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 7037-7045. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16866

Issue

Section

AAAI Technical Track on Machine Learning I