請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68252
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 | Chih-Yao Chang | en |
dc.contributor.author | 張智堯 | zh_TW |
dc.date.accessioned | 2021-06-17T02:15:47Z | - |
dc.date.available | 2018-01-04 | |
dc.date.copyright | 2018-01-04 | |
dc.date.issued | 2017 | |
dc.date.submitted | 2017-10-16 | |
dc.identifier.citation | M. Blondel, M. Ishihata, A. Fujino, and N. Ueda. Polynomial networks and factorization machines: new insights and e cient training algorithms. In Proceedings of the 33rd International Conference on Machine Learning (ICML), 2016.
S. Boyd and L. Vandenberghe. Convex Optimization. Cambridge University Press,2004. R. H. Byrd, G. M. Chin, W. Neveitt, and J. Nocedal. On the use of stochastic Hessian information in optimization methods for machine learning. SIAM J. Optim., 21(3):977-995, 2011. W. Chen, Z. Wang, and J. Zhou. Large-scale L-BFGS using MapReduce. In NIPS, 2014. W.-S. Chin, B.-W. Yuan, M. Y. Yang, and C.-J. Lin. An e cient alternating newton method for learning factorization machines. Preprint MCS-P153-0694, National Taiwan University, 2016. C.-Y. Hsia, Y. Zhu, and C.-J. Lin. A study on trust region update rules in newton methods for large-scale linear classi cation. Technical report, Department of Computer Science and Information Engineering, National Taiwan University, 2017. URL http://www.csie.ntu.edu.tw/~cjlin/papers/newtron/newtron. pdf. C.-P. Lee, P.-W. Wang, W. Chen, and C.-J. Lin. Limited-memory commondirections method for distributed optimization and its application on empirical risk minimization. In Proceedings of SIAM International Conference on Data Mining (SDM), 2017. URL http://www.csie.ntu.edu.tw/~cjlin/papers/l-commdir/l-commdir.pdf. J. Nocedal and S. Wright. Numerical Optimization. Springer, second edition,2006. S. Rendle. Factorization machines. In ICDM, 2010. C.-C. Wang, C.-H. Huang, and C.-J. Lin. Subsampled Hessian Newton methods for supervised learning. Neural Comput., 27:1766-1795, 2015. P.-W. Wang, C.-P. Lee, and C.-J. Lin. The common directions method for regularized empirical loss minimization. Technical report, National Taiwan University, 2016. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68252 | - |
dc.description.abstract | 近年來,非凸最佳化問題變得相當熱門。非凸最佳化問題是個充滿許多未知數的領域,也非常值得花費力氣去研究最佳化方法在這類問題上的行為模式。此外,分解機器也漸漸廣泛地被使用在各類型的應用上面,特別是推薦系統。為了深入了解,我們分析了交替牛頓法以及常見方向在分解機器上的行為。本作品的主要貢獻是:詳細的比較了模型之間的相對目標函式值、訓練時間、偽數據遍歷。實驗結果顯示交替常見方向在收斂速度上較交替牛頓法來的快。 | zh_TW |
dc.description.abstract | Recently, non-convex optimization has been a popular domain. Non-convex optimization
is a domain full of unknowns and it is worth investigating behaviors of optimzation techniques on such kind of problems. Also, Factorization Machine has also been a popular model in many applications, especially for recommendation systems. To know the details, we analyze the behaviors of alternating Newton method (ANT) and alternating common-directions method on the model. In this work, we compare their relative objective function value, training time, and pseudo data passe. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T02:15:47Z (GMT). No. of bitstreams: 1 ntu-106-R04922044-1.pdf: 3802436 bytes, checksum: 997cfae69a15505a95e6ab1990c3aebd (MD5) Previous issue date: 2017 | 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 : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : viii CHAPTER I. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 II. Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1 Alternating Minimization Methods . . . . . . . . . . . . . . . . 3 2.1.1 Alternating Minimization Framework . . . . . . . . . 3 2.1.2 Information Needed in Optimization Procedures . . . 4 2.1.3 Newton Methods for Solving Sub-problems . . . . . . 7 2.1.4 Alternating Newton Methods . . . . . . . . . . . . . . 8 2.1.5 Common Direction and L-Common Direction . . . . . 8 III. Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.1 Data Sets and Parameters . . . . . . . . . . . . . . . . . . . . . 15 3.2 Environment and Implementation . . . . . . . . . . . . . . . . 16 3.3 Comparison Between Dierent Methods . . . . . . . . . . . . . 16 3.4 Dierent Number of Directions . . . . . . . . . . . . . . . . . . 18 3.5 Sub-Problem W . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.6 Sub-Problem V . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 IV. Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 V. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 BIBLIOGRAPHY : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 46 | |
dc.language.iso | en | |
dc.title | 大規模分解機器之最佳化方法比較 | zh_TW |
dc.title | A Comparison of Optimization Methods for Large
Scale Factorization Machine | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林軒田(Hsuan-Tien Lin),李育杰(Yuh-Jye Lee) | |
dc.subject.keyword | 交替架構,牛頓法,常見方向方法,分解機器, | zh_TW |
dc.subject.keyword | alternating framework,Newton method,common-directions method,Factorization Machine, | en |
dc.relation.page | 47 | |
dc.identifier.doi | 10.6342/NTU201704285 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2017-10-16 | |
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-106-1.pdf 目前未授權公開取用 | 3.71 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。