改进图结构优化的近似Frank-Wolfe算法，提升迭代效率。
Approximate FW Algorithm with a novel DMO method over Graph-structured Support Set
- 引入回溯线搜索减少迭代次数
- 提出新DMO方法（Top-g+最优访问）但效果有限
- 适用于图结构凸优化问题的高效求解
本项目研究了基于近似Frank-Wolfe（FW）算法的图结构凸优化（GSCO）问题。分析并实现了原始算法，进一步提出扩展方案。实验表明，所提出的回溯线搜索方法有效降低了迭代次数；而新提出的DMO方法（Top-g+最优访问）虽有设计，但性能提升不显著。
原文摘要 · Abstract (English)
In this project, we reviewed a paper that deals graph-structured convex optimization (GSCO) problem with the approximate Frank-Wolfe (FW) algorithm. We analyzed and implemented the original algorithm and introduced some extensions based on that. Then we conducted experiments to compare the results and concluded that our backtracking line-search method effectively reduced the number of iterations, while our new DMO method (Top-g+ optimal visiting) did not make satisfying enough improvements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。