.png){kind=icon}
.png){kind=icon}
Return
Distributed and Parallel ADMM for Structured Nonconvex Optimization Problem
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2019.2950337.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The nonconvex optimization problems have recently attracted significant attention. However, both efficient algorithm and solid theory are still very limited. The difficulty is even pronounced for structured large-scale problems in many real-world applications. This article proposes an application-driven algorithmic framework for structured nonconvex optimization problems with distributed and parallel techniques, which jointly handles the high dimensionality of model parameters and distributed training data. The theoretical convergence of our algorithm is established under moderate assumptions. We apply the proposed method to popular multitask applications, including a multitask reinforcement learning problem. The promising performance demonstrates our framework is effective and efficient.
Keywords:
Task analysis
Optimization
Convergence
Linear programming
Machine learning
Signal processing algorithms
Minimization
Distributed
large-scale optimization
multitask reinforcement learning
nonconvex optimization
parallel
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W