|
|||||
|
|
| 一种连续的谱聚类优化模型 | |
| 引用本文： | 刘歆,吴国宝,张瑞,张在坤.一种连续的谱聚类优化模型[J].计算数学,2018,40(4):354-366. |
| 作者姓名： | 刘歆 吴国宝 张瑞 张在坤 |
| 作者单位： | 1. 中国科学院数学与系统科学研究院, 科学与工程计算国家重点实验室, 北京 100190; 2. 中国科学院大学, 北京 100190; 3. 香港浸会大学数学系; 4. 香港理工大学应用数学系 |
| 基金项目： | 国家自然科学基金项目（11622112，11471325，91530204和11688101）；国家数学与交叉科学中心；香港研究资助局（RGC）基金项目（PolyU 253012/17P，N_PolyU504/14，HKBU RC-ICRS/16-17/03）；香港理工大学科研启动基金项目1-ZVHT资助. |
| 摘 要： | 聚类与图的划分问题在大数据分析中有着重要的应用.这类问题一般被描述为组合优化问题,因此较难快速求解.本文设计了一种新的连续优化模型,并提出了一种块坐标下降算法,数值实验显示我们的新方法在求解聚类与图的划分问题上很有潜力.我们还更进一步分析了我们的连续优化模型和组合优化模型的关系. |
| 关 键 词： | 聚类 图的划分 块坐标下降 |
A NEW CONTINUOUS OPTIMIZATION MODEL FOR SPECTRAL CLUSTERING |
|
| Liu Xin,Michael Ng,Zhang Rui,Zhang Zaikun.A NEW CONTINUOUS OPTIMIZATION MODEL FOR SPECTRAL CLUSTERING[J].Mathematica Numerica Sinica,2018,40(4):354-366. | |
| Authors: | Liu Xin Michael Ng Zhang Rui Zhang Zaikun |
| Institution: | 1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China; 2. University of Chinese Academy of Sciences, Beijing 100190, China; 3. Hong Kong Baptist University, China; 4. Hong Kong Polytechnic University, China |
| Abstract: | Clustering and graph partition play an important role in big data analysis. These problems are often formulated as combinatorial optimization models. Consequently, to solve them efficiently is difficult. In this paper, we propose a novel continuous optimization model, and a block coordinate decent method to solve it. Numerical experiments show that the new approach has great potential in dealing with clustering and graph partition problems. We also give preliminary analysis on the relationship between our model and the original combinatorial optimization model. |
| Keywords: | Clustering graph partition block coordinate decent |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《计算数学》浏览原始摘要信息 | |
| 点击此处可从《计算数学》下载免费的PDF全文 | |