請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51324完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林智仁(Chih-Jen Lin) | |
| dc.contributor.author | Wei-Lun Huang | en |
| dc.contributor.author | 黃煒倫 | zh_TW |
| dc.date.accessioned | 2021-06-15T13:30:33Z | - |
| dc.date.available | 2019-03-08 | |
| dc.date.copyright | 2016-03-08 | |
| dc.date.issued | 2016 | |
| dc.date.submitted | 2016-02-03 | |
| dc.identifier.citation | [1] A. Agarwal, O. Chapelle, M. Dudik, and J. Langford. A reliable effective terascale linear learning system. Journal of Machine Learning Research, 15:1111-1133, 2014.
[2] A. Airola, T. Pahikkala, and T. Salakoski. Training linear ranking SVMs in linearithmic time using red-black trees. Pattern Recognition Letters, 32(9):1328-1336, 2011. [3] B. E. Boser, I. Guyon, and V. Vapnik. A training algorithm for optimal margin classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pages 144-152. ACM Press, 1992. [4] C. J. C. Burges. From RankNet to LambdaRank to LambdaMART: An overview. Technical Report MSR-TR-2010-82, Microsoft Research, 2010. [5] Y.-W. Chang, C.-J. Hsieh, K.-W. Chang, M. Ringgaard, and C.-J. Lin. Training and testing low-degree polynomial data mappings via linear SVM. Journal of Machine Learning Research, 11:1471-1490, 2010. URL http://www.csie.ntu.edu.tw/~cjlin/papers/lowpoly_journal.pdf. [6] O. Chapelle and Y. Chang. Yahoo! learning to rank challenge overview. In JMLR Workshop and Conference Proceedings: Workshop on Yahoo! Learning to Rank Challenge, volume 14, pages 1-24, 2011. [7] O. Chapelle and S. S. Keerthi. Efficient algorithms for ranking with SVMs. Information Retrieval, 13(3):201-215, 2010. [8] D. Christensen. Fast algorithms for the calculation of Kendall's tau. Computational Statistics, 20:51-62, 2005. [9] C. Cortes and V. Vapnik. Support-vector network. Machine Learning, 20:273-297, 1995. [10] R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. LIBLINEAR: a library for large linear classi cation. Journal of Machine Learning Research, 9:1871-1874, 2008. URL http://www.csie.ntu.edu.tw/~cjlin/papers/liblinear.pdf. [11] E. Gabriel, G. E. Fagg, G. Bosilca, T. Angskun, J. J. Dongarra, J. M. Squyres, V. Sahay, P. Kambadur, B. Barrett, A. Lumsdaine, R. H. Castain, D. J. Daniel, R. L. Graham, and T. S.Woodall. Open MPI: Goals, concept, and design of a next generation MPI implementation. In Proceedings of the 11th European PVM/MPI Users' Group Meeting, pages 97-104, 2004. [12] R. Herbrich, T. Graepel, and K. Obermayer. Large margin rank boundaries for ordinal regression. In P. J. Bartlett, B. Sch olkopf, D. Schuurmans, and A. J. Smola, editors, Advances in Large Margin Classifiers, pages 115-132. MIT Press, 2000. [13] J. Jin. Mail from Jing Jin (personal communication), 2015. [14] J. Jin and X. Lin. Efficient parallel algorithms for linear ranksvm on GPU. In C. Hsu, X. Shi, and V. Salapura, editors, Network and Parallel Computing - 11th IFIP WG 10.3 International Conference, NPC 2014, Ilan, Taiwan, September 18-20, 2014. Proceedings, volume 8707 of Lecture Notes in Computer Science, pages 181-194. Springer, 2014. doi: 10.1007/978-3-662-44917-2 16. URL http://dx.doi.org/10.1007/978-3-662-44917-2_16. [15] T. Joachims. A support vector method for multivariate performance measures. In Proceedings of the Twenty Second International Conference on Machine Learning (ICML), 2005. [16] T. Joachims. Training linear SVMs in linear time. In Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2006. [17] S. S. Keerthi and D. DeCoste. A modi ed nite newton method for fast solution of large scale linear svms. Journal of Machine Learning Research, 6:341-361, 2005. URL http://dblp.uni-trier.de/db/journals/jmlr/jmlr6.html#KeerthiD05. [18] C.-P. Lee and C.-J. Lin. Large-scale linear rankSVM. Neural Computation, 26(4): 781-817, 2014. URL http://www.csie.ntu.edu.tw/~cjlin/papers/ranksvm/ranksvml2.pdf. [19] C.-J. Lin, R. C. Weng, and S. S. Keerthi. Trust region Newton method for largescale logistic regression. In Proceedings of the 24th International Conference on Machine Learning (ICML), 2007. Software available at http://www.csie.ntu.edu.tw/~cjlin/liblinear. [20] C.-J. Lin, R. C. Weng, and S. S. Keerthi. Trust region Newton method for largescale logistic regression. Journal of Machine Learning Research, 9:627-650, 2008. URL http://www.csie.ntu.edu.tw/~cjlin/papers/logistic.pdf. [21] C.-Y. Lin, C.-H. Tsai, C.-P. Lee, and C.-J. Lin. Large-scale logistic regression and linear support vector machines using Spark. In Proceedings of the IEEE International Conference on Big Data, pages 519-528, 2014. URL http://www.csie.ntu.edu.tw/~cjlin/papers/spark-liblinear/spark-liblinear.pdf. [22] O. L. Mangasarian. A nite Newton method for classi cation. Optimization Methods and Software, 17(5):913-929, 2002. [23] M. Snir and S. Otto. MPI-the complete reference: the MPI core. MIT Press, Cambridge, MA, USA, 1998. [24] G.-X. Yuan, C.-H. Ho, and C.-J. Lin. Recent advances of large-scale linear classification. Proceedings of the IEEE, 100(9):2584-2603, 2012. URL http://www.csie.ntu.edu.tw/~cjlin/papers/survey-linear.pdf. [25] Y. Zhuang, W.-S. Chin, Y.-C. Juan, and C.-J. Lin. Distributed Newton method for regularized logistic regression. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51324 | - |
| dc.description.abstract | 在排序學習中，要快速地得到一個基準模型作為比較，線性排序支持向量機是一個有用的方法。雖然它的平行機制已經被探討且實作在圖形處理器上面，但此實作有可能無法處理大規模的數據集。在本論文中，我們提出兩種平行架構，用分散式牛頓法訓練L2損失函數之線性排序支持向量機。我們小心的探討降低溝通成本以及加速運算的技術，並且在稠密和稀疏的數據集上比較兩種平行機制的優劣。實驗顯示本文提出的方法在兩種數據集上會遠比單機運算快，分別為資料量遠大於特徵數以及特徵數遠大於資料量的數據集。 | zh_TW |
| dc.description.abstract | Linear rankSVM is a useful method to quickly produce a baseline model for learning to rank. Although its parallelization has been investigated and implemented on GPU, it may not handle large-scale data sets. In this thesis, we propose a distributed trust region Newton method for training L2-loss linear rankSVM with two kinds of parallelizations. We carefully discuss the techniques for reducing the communication cost and speeding up the computation, and compare both kinds of parallelizations on dense and sparse data sets. Experiments show that our distributed methods are much faster than the single machine method on two kinds of data sets: one with its number of instances much larger than its number of features, and the other is the opposite. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T13:30:33Z (GMT). No. of bitstreams: 1 ntu-105-R02922041-1.pdf: 6624881 bytes, checksum: bb7aa5ee5b7081159349dbe594623abd (MD5) Previous issue date: 2016 | en |
| dc.description.tableofcontents | 口試委員會審定書 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
中文摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii CHAPTER I. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 II. Efficient Computation of Linear RankSVM and Distributed Trust Region Newton Methods . . . . . . . . . . . . . . . . . . . . 6 2.1 Trust Region Newton Methods (TRON) . . . . . . . . . . . . . 6 2.2 Efficient Evaluation for Function/Gradient and Hessian-vector Products . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Query-wise Function/Gradient and Matrix-vector Products Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.4 Query-wise and Feature-wise Data Splits . . . . . . . . . . . . . 14 2.4.1 Query-wise Split . . . . . . . . . . . . . . . . . . . . . 15 2.4.2 Feature-wise Split . . . . . . . . . . . . . . . . . . . . 16 2.4.3 Comparison between Query-wise and Feature-wise Splits 17 2.5 Implementation Techniques . . . . . . . . . . . . . . . . . . . . 18 III. Comparison with Related Works . . . . . . . . . . . . . . . . . . . 21 3.1 GPU Linear rankSVM . . . . . . . . . . . . . . . . . . . . . . . 21 3.2 DRANKSVM . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 3.3 Distributed TRON on Logistic Regression . . . . . . . . . . . . 23 3.3.1 Logistic Regression . . . . . . . . . . . . . . . . . . . 24 3.3.2 Instance-wise and Feature-wise Data Split . . . . . . . 24 3.3.3 Instance-wise Split . . . . . . . . . . . . . . . . . . . . 25 3.3.4 Feature-wise Split . . . . . . . . . . . . . . . . . . . . 25 3.3.5 Comparison Between Distributed Logistic Regression and Linear RankSVM . . . . . . . . . . . . . . . . . . 26 IV. Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.1 Experiment Settings . . . . . . . . . . . . . . . . . . . . . . . . 28 4.2 Low-Degree Polynomial Expansion on Sparse Data Sets . . . . 30 4.2.1 Implementation Details . . . . . . . . . . . . . . . . . 31 4.2.2 Comparison Between Non-Expanded and Expanded Sparse Data Sets on Training Time and Test Accuracy 32 4.3 Comparison Between TreeTron-qw-noacc and TreeTron-qw on Training Time . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 4.4 Comparison Between TreeTron-qw, TreeTron-fw, and TreeTron on Function Values . . . . . . . . . . . . . . . . . . . . . . . . . 34 4.5 Comparison Between TreeTron-qw, TreeTron-fw, and TreeTron on Test Pairwise Accuracy . . . . . . . . . . . . . . . . . . . . 38 4.6 Speedup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 V. Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 BIBLIOGRAPHY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 | |
| dc.language.iso | en | |
| dc.subject | 大規模學習 | zh_TW |
| dc.subject | 排序支持向量機 | zh_TW |
| dc.subject | 分散式牛頓法 | zh_TW |
| dc.subject | 大規模學習 | zh_TW |
| dc.subject | 排序支持向量機 | zh_TW |
| dc.subject | 分散式牛頓法 | zh_TW |
| dc.subject | Distributed Newton method | en |
| dc.subject | Learning to rank | en |
| dc.subject | Ranking support vector machines | en |
| dc.subject | Large-scale learning | en |
| dc.subject | Linear model | en |
| dc.subject | Distributed Newton method | en |
| dc.subject | Learning to rank | en |
| dc.subject | Ranking support vector machines | en |
| dc.subject | Large-scale learning | en |
| dc.subject | Linear model | en |
| dc.title | 大規模線性排序支持向量機在分散式環境下之分析實作 | zh_TW |
| dc.title | Analysis and Implementation of Large-scale Linear RankSVM in Distributed Environments | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 104-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林軒田(Hsuan-Tien Lin),李育杰(Yuh-Jye Lee) | |
| dc.subject.keyword | 大規模學習,排序支持向量機,分散式牛頓法, | zh_TW |
| dc.subject.keyword | Learning to rank,Ranking support vector machines,Large-scale learning,Linear model,Distributed Newton method, | en |
| dc.relation.page | 48 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2016-02-03 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 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-105-1.pdf 未授權公開取用 | 6.47 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。