Kyushu University Academic Staff Educational and Research Activities Database
Researcher information (To researchers) Need Help? How to update
Kohei Hatano Last modified date:2018.06.15



Graduate School
Other Organization
Other


E-Mail
Homepage
https://sites.google.com/view/koheihatano/home
Phone
092-802-6031
Academic Degree
Ph.D
Country of degree conferring institution (Overseas)
No
Field of Specialization
machine learning
ORCID(Open Researcher and Contributor ID)
0000-0002-1536-1269
Total Priod of education and research career in the foreign country
00years03months
Outline Activities
My main research interest includes Machine Learning, in particular, design and analyses of robust and efficient machine learning algorithms from a theoretical perspective. I am also affiliated with Department of Informatics and the Learning Analytics Center for analyzing educational data.
Research
Research Interests
  • Open Science
    keyword : open access, open data, open science
    2015.08.
  • Design and analysis of online prediction algorithms
    keyword : online learning, computational learning theory, machine learning, optimization, ranking
    2007.05.
  • Analysis and depelopment of boosting algorithms
    keyword : boosting, machine learning, computational learning theory, data mining
    2000.04[Theoretical analyses of boosting methods] Boosting is a technique for constructing a highly accurate classifier by combining many ``weak'' classifiers. Although boosting has become a fundamental tool in machine learning and data mining these days, its theoretical propeties are yet to be understood. We have analysed theoretical properties of boosting in order to design more efficient boosting methods. As a result, we clarified a property which might be a key for further improvement. So far, we are developping a new boosting algorithm based on our analysis..
Academic Activities
Books
1. Boosting - methods for design of learning algorithms -.
Reports
1. , [URL].
2. Report on The 21st Annual Conference on Learning Theory (COLT 2008) .
3. Frontier of Theoretical Computer Science.
Papers
1. Takahiro Fujita, Kohei Hatano, and Eiji Takimoto, “, Online Combinatorial Optimization with Multiple Projections and Its Application to Scheduling Problem
Volume and Number: Vol.,pp.-,Sep. 2018., IEICE Transactions on Information and Systems, E101-A, 9, 2018.09.
2. Ken-ichiro Moridomi, Kohei Hatano, and Eiji Takimoto, “, Tighter generalization bounds for matrix completion via factorization into constrained matrices, IEICE Transactions on Information and Systems, E101-D, 8 , 2018.08.
3. Ken-ichiro Moridomi, Kohei Hatano, and Eiji Takimoto, “, Online linear optimization with the log-determinant regularizer, IEICE Transactions on Information and Systems, E101-D, 6, 2018.06.
4. Takahiro Fujita, Kohei Hatano, Eiji Takimoto, Boosting over non-deterministic ZDDs, Proceedings of the 12th International Conference and Workshop on Algorithms and Computation( WALCOM 2018), https://doi.org/10.1007/978-3-319-75172-6_17, 195-206, 2018.01, 本論文では,ZDDと呼ばれる圧縮データ構造を用いてデータを圧縮した上で,圧縮したデータ上でブースティングという機械学習手法が効率よく計算できる事を明らかにした.ビッグデータの解析において,省スペースで計算が出来ることは大きな利点である.本研究の興味深い点は,組合せ論的オンライン予測という(一見)全く異なる機械学習分野の知見が圧縮情報処理に活かされたことである..
5. Daiki Suehiro, Kohei hatano, Eiji Takimoto, Efficient reformulation of 1-norm ranking SVM, IEICE Transactions on Information and Systems, https://doi.org/10.1587/transinf.2017EDP7233, E101D, 3, 719-729, 2018.03.
6. Takumi Nakazono, Ken-ichiro Moridomi, Kohei Hatano, Eiji Takimoto, A Combinatorial Metrical Task System Problem under the Uniform Metric, Proceedings of 27th International Conference on Algorithmic Learning Theory(ALT 2016), 10.1007/978-3-319-46379-7_19, LNCS 9926, 276-287, 2016.10.
7. Nir Ailon, Kohei Hatano, Eiji Takimoto, Bandit Online Optimization Over the Permutahedron, Theoretical Computer Science, 10.1016/j.tcs.2016.07.033, 650, 18, 92-108, 2016.10.
8. Issei Matsumoto, Kohei Hatano, Eiji Takimoto, Online Density Estimation of Bradley-Terry Models, Proceedings of the 28th Conference on Learning Theory (COLT 2015), JMLR W&CP 40, 1343-1359, 2015.06.
9. Takahiro Fujita, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Online Linear Optimization for Job Scheduling under Precedence Concstraints, Proceedings of 26th International Conference on Algorithmic Learning Theory(ALT 2015), 10.1007/978-3-319-24486-0_22, LNCS 6331, 345-359, 2015.10.
10. Nir Ailon, Kohei Hatano, Eiji Takimoto, Bandit Online Optimization Over the Permutahedron, Proceedings of the 25th International Conference on Algorithmic Learning Theory (ALT 2014),, LNCS 8776, 215–229, 2014.10.
11. Kazuki Teraoka, Kohei Hatano, Eiji Takimoto, Efficient Sampling Method for Monte Carlo Tree Search, IEICE TRANSACTIONS on Information and System, E97-D, 3, 392-298, 2014.03.
12. Takahiro Fujita, Kohei Hatano, Eiji Takimoto, Combinatorial Online Prediction via Metarounding, Proceedings of the 24th International Conference on Algorithmic Learning Theory (ALT 2013), 68-82, 2013.10.
13. Shota Yasutake, Kohei Hatano, Eiji Takimoto, Masayuki Takeda, Online Rank Aggregation
, Proceedings of the 4th Asian Conference on Machine Learning(ACML 2012) , 539-553, 2012.11.
14. Daiki Suehiro, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Kiyohito Nagano, Online Prediction under Submodular Constraints, Proceedings of the 23rd International Conference on Algorithmic Learning Theory (ALT 2012) , 260-274, 2012.10.
15. Yoko Anan, Kohei Hatano, Hideo Bannai, Masayuki Takeda, Polyphonic Music Classification on Symbolic Data Using Dissimilarity Functions, Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR 2012), 229-234, 2012.10.
16. Shota Yasutake, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Masayuki Takeda, , Online Linear Optimization over Permutations
, Proceedings of the 22nd International Symposium on Algorithms and Computation (ISAAC 2011) , 534-543, 2011.11.
17. Shin-ichi Yoshida, Kohei Hatano, Eiji Takimoto, Masayuki Takeda, Adaptive Online Prediction Using Weighted Windows, IEICE Transactions on Information and Systems , E94-D, 10, 1917-1923, 2011.10.
18. Yoko Anan, Kohei Hatano, Hideo Bannai, Masayuki Takeda, Music Genre Classification using Similarity Functions, Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011), 693-698, 2011.10.
19. Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Approximate Reduction from AUC Maximization to 1-norm Soft Margin Optimization, Proceedings of the 22nd International Conference on Algorithmic Learning Theory (ALT 2011) , 324-337, 2011.10.
20. Michinari Momma, Kohei Hatano, and Hiroki Nakayama, Ellipsoidal Support Vector Machines
, Proceedings of the 2nd Asian Conference on Machine Learning (ACML 2010), 31-46, 2010.11.
21. Kazuaki Kashihara, Kohei Hatano, Hideo Bannnai, and Masayuki Takeda, Sparse Substring Pattern Set Discovery using Linear Programming Boosting, Proceedings of the 13th International Conference on Discovery Science (DS 2010), 132-143, 2010.10.
22. Kohei Hatano and Eiji Takimoto, Linear Programming Boosting by Column and Row Generation, Proceedings of the Twelfth International Conference on Discovery Science (DS'09) , 2009.10.
23. Jun-ichi Moribe, Kohei Hatano, Eiji Takimoto, and Masayuki Takeda, Smooth Boosting for Margin-Based Ranking, Proceedings of 19th International Conference on Algorithmic Learning Theory, 227-239, 2008.10.
24. Kosuke Ishibashi, Kohei Hatano, and Masayuki Takeda, Online Learning of Approximate Maximum p-Norm Margin Classifiers with Biases, Proceedings of the 21st Annual Conference on Learning Theory, 69—80, 2008.07.
25. Kosuke Ishibashi, Kohei Hatano, and Masayuki Takeda, Online Learning of Approximate Maximum Margin Classifiers with Biases, Proceedings of the 2nd International Workshop on Data Mining and Statistical Science, 2007.10.
26. Kohei Hatano, Smooth Boosting Using an Information-based Criterion, The 17 th international conference on algorithmic learning theory, 10.1007/11894841_25, 304-318, LNAI 4264., 2006.10.
Presentations
1. , [URL].
2. Takahiro Fujita, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Online Linear Optimization over Permutations with Precedence Constraints

, NIPS 2014 Workshop on Discrete Optimization in Machine Learning(DISCML), 2014.12.
3. Issei Matsumoto, Kohei Hatano, Eiji Takimoto, Online Prediction with Bradley-Terry Models, NIPS 2014 Workshop on Analysis of Rank Data: Confluence of Social Choice, Operations Research, and Machine Learning, 2014.12.
4. 畑埜 晃平, Combinatorial Online Prediction via Metarounding, TCE Guest Lecture, 2013.12.
5. Takahiro Fujita, Kohei Hatano, Eiji Takimoto, Combinatorial Online Prediction Using Offline Approximation Algorithms, The sixth Annual Meeting of Asian Association for Algorithms and Computation (AAAC2013), 2013.04.
6. Daiki Suehiro, Kohei Hatano, Shuji Kijima, Eiji Takimoto, Kiyohito Nagano, Online Prediction over Base Polyhedra

, NIPS 2012 Workshop on Discrete Optimization in Machine Learning(DISCML), 2012.12.
7. Online Rank Aggregation.
8. Online Rank Aggregation.
9. Learning evaluation functions for Shogi via bipertite ranking learning with SVMs .
10. Learning evaluation functions for Shogi via bipertite ranking learning with SVMs .
11. Online Rank Aggregation.
12. Online Rank Aggregation.
13. Online Learning Based On Maximum Entropy Principle.
14. Online Learning of Maximum p-Norm Margin Classifiers with Bias.
15. Efficient online learning of linear threshold functions with large biases..
16. Boosting using classifiers with nearly one-sided error.
Membership in Academic Society
  • EATCS
  • IEICE
  • LA
Awards
  • We show that one of machine learning techniques called “boosting” can be efficiently computed over compressed data using non-determinist Zero-Suppressed Binary Decision Diagrams (ZDDs). A big advantage of this scheme is the ability to perform analysis using big data with minimal space. An interesting point in this research is that the combinatorial online prediction, a seemingly unrelated machine learning concept is successfully adopted for utilizing compressed data.
  • JSAI Incentive Award
  • JSAI Incentive Award
Educational
Educational Activities
Teaching and supervising in exercises of undergraduate classes and graduate seminars at Department of Informatics and Department of Library Science.