Yasushi Kawase

Posted on 2020年10月9日2020年10月9日 by keisu-editor

Profile

Yasushi Kawase

Project Associate Professor

Department of Mathematical Informatics, Graduate School of Information Science and Technology

RIISE: Research Institute for an Inclusive Society through Engineering

Room 436, Engineering Bldg. 6, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656
Tel: 03-5841-0698 (ext. 20698)
Fax: 03-5841-0698

E-mail：kawase＠mist.i.u-tokyo.ac.jp

[Home page]

Biography

March 2009	Bachelor of Engineering, Department of Mathematical Engineering and Information Physics, School of Engineering, The University of Tokyo
March 2011	Master of Information Science and Technology, Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
March 2014	Doctor of Information Science and Technology, Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
April 2014	Assistant Professor, Department of Social Engineering, Graduate School of Decision Science and Technology, Tokyo Institute of Technology
April 2016	Assistant Professor, Department of Industrial Engineering and Economics, School of Engineering, Tokyo Institute of Technology
October 2020	Project Associate Professor, Graduate School of Information Science and Technology, The University of Tokyo

Research Themes

(1) Discrete optimization: Design of algorithms for online optimization problems, robust optimization problems, etc.

(2) Algorithmic game theory: Design and analysis of mechanisms in strategic behavior.

Selected Publications

– Yasushi Kawase and Atsushi Iwasaki: Approximately Stable Matchings with General Constraints, Proceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS2020), Pages 602–610, May 2020.
– Yasushi Kawase and Hanna Sumita: Randomized Strategies for Robust Combinatorial Optimization, Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI2019), Pages 7876–7883, January 2019
– Yasushi Kawase, Kazuhisa Makino, and Kento Seimi: Optimal Composition Ordering Problems for Piecewise Linear Functions, Algorithmica, Vol. 80, Issue 7, Pages 2134–2159, July 2018
– Xin Han, Yasushi Kawase, and Kazuhisa Makino: Online Unweighted Knapsack Problem with Removal Cost, Algorithmica, Vol. 70, Pages 76–91, September 2014.

Mathematical Informatics Lab. 6

Posted on 2020年5月7日2020年5月7日 by keisu-editor

Mathematical Informatics (Lab. 6)

HomePage→

Kenji Yamanishi Professor	Taiji Suzuki Associate Professor
Ryohei Hisano Lecturer

Information-theoretic learning theory/Statistical learning theory: “What are the possibility and limitation of machine learning?” We take
information-theoretic and statistical approaches to answer this
question. As for information-theoretic learning theory, we study a
unifying methodology for model selection, representation learning,
change detection, high-dimensional sparse learning, etc. on the basis
of the minimum description length principle. As for statistical
learning, we study new algorithm designs and theoretical analysis of
deep learning and kernel methods on the basis of statistical theory.
We also develop new optimization methods to run the machine learning
algorithms efficiently on the big data.
Data Science Foundation: We study methodologies for knowledge discovery from big data (anomaly
detection, network mining, embedding, etc.) Specifically we are
interested in discovering deep knowledge from latent spaces. We aim at
building a new field called “Symptomatics”, in which we detect signs
of latent changes in future from data streams.
Data Science Applications: We study effective data science methodologies by applying machine
learning and data mining technologies to real complex data. The
applications include economics, financial data analysis, medical data
analysis, marketing, SNS data analysis, failure detection, spatial
data mining, security, etc. We often collaborate with industrial
companies to solve real data science problems.

Lab 6. Ryohei Hisano

Posted on 2020年4月10日2020年4月10日 by suuri6

Profile

Ryohei Hisano

Mathematics and Informatics Center, Graduate School of Information Science and Technology, The University of Tokyo
Lecturer

Room 214B, Engineering Bldg. 12, 2-5-37, Ikenohata, Taito-ku, Tokyo 110-0008
Tel:

E-mail: hisano@mist.i.u-tokyo.ac.jp

[Personal Site]

Biography

March 2007	Bachelor degree from Department of Economics, Keio University
March 2010	Master’s degree from Graduate School of Economics, Hitotsubashi University
August 2013	D-MTEC (Dr. Sc. ETH Zürich) from ETH Zürich
Sept. 2013	Postdoctoral researcher, ETH Zürich, D-MTEC
Oct. 2013	Postdoctoral researcher, The National Institute of Informatics
April 2014	JSPS Research Fellow, Graduate School of Economics, The University of Tokyo
December 2015	Specially Appointed Research Associate, Graduate School of Information Science and Technology, The University of Tokyo
April 2020	Lecturer, Mathematics and Informatics Center, Graduate School of Information Science and Technology, The University of Tokyo

Research Topics

My research interests lie in both empirical research and statistical model building of social and economic big data. On the empirical research side, my research has mainly focused on analyzing datasets primarily in finance and macroeconomics domain (financial markets, blockchain, news text, financial statements, firm networks, sales of products), but this does not mean that I am solely interested in economics. For the statistical modeling side, my focus is on developing models that take into account various characteristics and empirical regularities found in the economy and utilizing information from multiple sources in the form of a heterogeneous information network. For the latter model building research, I mainly develop network mining (simple, temporal, heterogeneous information network) and text mining methods.
By combining the two research topics, my goal is to model complex issues in society (e.g., propagation and mitigation of shocks, hidden industrial block structure, aggregate fluctuation, matching among firms, network formation, bubbles, crashes, financial statements, systemic risks, the velocity of money, news events and reliability of information) to not only contribute to academic research but better understand risks and accelerate evidence-based policymaking.

Selected Publications

Ryohei Hisano, Didier Sornette, Takayuki Mizuno , “Prediction of ESG compliance using a heterogeneous information network”, Journal of Big Data 7, 22, 2020.
Ryohei Hisano, “Learning Topic Models by Neighborhood Aggregation”, IJCAI 2019, Macao, China, Aug 10 -16, 2019.
Ryohei Hisano, “Semi-supervised Graph Embedding Approach to Dynamic Link Prediction”, Complenet 2018, Northeastern University, Boston, Match 4-8, 2018. In: Sean Cornelius, Kate Coronges, Bruno Gonçalves, Roberta Sinatra, Alessandro Vespignani (Eds.), Complex Networks IX. Springer Proceedings in Complexity, page 109-121, 2018.
Ryohei Hisano, Tsutomu Watanabe, Takayuki Mizuno, Takaaki Ohnishi, Didier Sornette, “The gradual evolution of buyer-seller networks and their role in aggregate fluctuations”, Applied Network Science, Vol 2, 9, 2017.
Ryohei Hisano, “A new approach to building the interindustry input-output table using block estimation techniques”, 2016 IEEE International Conference on Big Data (Big Data), Workshop Application of Big Data for Computational Social Science, 5-8 Dec. 2016.