Description : This package includes the python code of the DPOSS algorithm [1]. This is a distributed version of our previous POSS algorithm [2] for the subset selection problem. DPOSS uses a two-round divide and conquer strategy and can be easily implemented in the MapReduce framework. A Readme file and two example files are included in the package. In the 'mc_distributed_algorithm.py' and 'sr_distributed_algorithm.py', you will find examples of using this code for the application of maximum coverage and sparse regression, respectively.

References: [1] Chao Qian, Guiying Li, Chao Feng, and Ke Tang. Distributed Pareto Optimization for Subset Selection. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI'18), Stockholm, Sweden, 2018. [2] Chao Qian, Yang Yu, and Zhi-Hua Zhou. Subset Selection by Pareto Optimization. In: Advances in Neural Information Processing Systems 28 (NIPS'15), Montreal, Canada, 2015

ATTN: This package is free for academic usage. You can run it at your own risk. For other purposes, please contact Dr. Chao Qian (chaoqian@ustc.edu.cn).

Requirement: The package was developed with python.

ATTN2: This package was developed by Mr. Guiying Li and Chao Feng ({lgy147, chaofeng}@mail.ustc.edu.cn). For any problem concerning the code, please feel free to contact them.

Download: code (1MB)