Abstract | ||
---|---|---|
Alternating direction method of multipliers (ADMM) is a widely used tool for machine learning in distributed settings where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns of data owners. The goal of this paper is to provide differential privacy for ADMM... |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TIFS.2019.2931068 | IEEE Transactions on Information Forensics and Security |
Keywords | Field | DocType |
Privacy,Differential privacy,Machine learning,Convergence,Convex functions,Standards,Approximation algorithms | Convergence (routing),Approximation algorithm,Mathematical optimization,Differential privacy,Iterative and incremental development,Pattern recognition,Computer science,Convex function,Augmented Lagrangian method,Artificial intelligence,Gaussian noise,Message passing | Journal |
Volume | ISSN | Citations |
15 | 1556-6013 | 7 |
PageRank | References | Authors |
0.45 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zonghao Huang | 1 | 11 | 2.14 |
Rui Hu | 2 | 7 | 0.45 |
Yuanxiong Guo | 3 | 60 | 5.90 |
Eric Chan-Tin | 4 | 229 | 15.79 |
Yanmin Gong | 5 | 133 | 16.82 |