請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41311
標題: | 對偶座標下降法求解線性支持向量機 Dual Coordinate Descent Methods for Large-scale Linear Support Vector Machines |
作者: | Kai-Wei Chang 張凱崴 |
指導教授: | 林智仁(Chih-Jen Lin) |
關鍵字: | 線性分類模型,線性支持向量機,座標下降法, Linear classification,Linear support vector machines,Coordinate descent, |
出版年 : | 2009 |
學位: | 碩士 |
摘要: | 在許多分類問題中,訓練資料量頗為龐大,不但資料筆數多,特徵值數量也不少,線性支持向量機是一個處理大型分類問題的熱門訓練模型。在論文中,我們提出一個新的對偶座標下降法,以求解一階及二階損失線性支持向量機,此方法不但簡單,且能在 O(log(1/e)個迭代內求得e精確度的最佳解。實驗結果顯示,與目前最先進的求解方法相比,如Pegasos、TRON、SVMperf,我們的方法能在更短的時間內求得解答。此外,我們還延伸對偶座標下降法,以求解大型多類分類問題,並且在本論文中介紹我們實做的LIBLINEAR軟體。 In many applications, data appear with a huge number of instances as well as features. Linear Support Vector Machines (SVM) is one of the most popular tools to deal with such large-scale sparse data. In this thesis, we present a novel dual coordinate descent method for linear SVM with L1- and L2-loss functions. The proposed method is simple and reaches an e-accurate solution in O(log (1/e)) iterations. Experiments indicate that our method is much faster than state of the art solvers such as Pegasos, TRON, SVMperf, and a recent primal coordinate descent implementation. In addition, we extended the proposed method to solve multi-class problems. We also describe our implementation for the software LIBLINEAR. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41311 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-98-1.pdf 目前未授權公開取用 | 2.31 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。