Masahiro Kato

I am a quantitative analyst and researcher. My work runs from applying statistics and machine learning to problems companies actually face, through to the methodological research underneath. I also run a company that provides employment support for people with disabilities.

At Mizuho-DL Financial Technology I work on data analysis and on developing new methods for it. Before that I was a research scientist at CyberAgent's AI Lab, where I worked on causal inference, density-ratio estimation, and anomaly detection. I hold research positions at Osaka Metropolitan University and RIKEN AIP.

My research centers on causal inference and adaptive experimental design: how to design an experiment and analyze it so that the decision you make afterwards holds up. Around that core, I work on density-ratio estimation and its use in anomaly detection and in learning from incomplete labels, on portfolio selection under model uncertainty, and on grounding what a large language model outputs in retrieved evidence and explicit computation. The topics below cover each of these.

Mizuho-DL Financial Technology · Osaka Metropolitan University · RIKEN AIP · WILL Inc.

Professional Experience

2026–

WILL Inc. (株式会社ウィル) — Representative Director. The company operates a Type B continuous employment support office and a group home for people with disabilities.

2026–

RIKEN AIP

2025–

Osaka Metropolitan University, Graduate School of Business — Visiting Researcher

2023–

Mizuho-DL Financial Technology Co., Ltd., Data Analytics Team — Financial Engineer

2020–2023

CyberAgent, Inc., AI Lab, Ad Econ Team — Research Scientist

Education

2021–

PhD candidate in Arts and Sciences, The University of Tokyo — Advised by Prof. Masaaki Imaizumi

2017–2020

MS in Computer Science, The University of Tokyo — Advised by Prof. Junya Honda and Prof. Masashi Sugiyama

2013–2017

BA in Economics, The University of Tokyo — Advised by Prof. Daisuke Oyama and Prof. Hidehiko Ichimura

Research Topics

Each page below states the problem the area addresses, what I have proposed, and which papers to read for the details. The first eight are the areas I work in most; the last four are narrower methodological threads that run through them.

• AI, LLMs, and Decision-Making

  Tying the output of a language model to retrieved evidence and to explicit model computation, so that the analysis behind a decision can be traced.

• AI-Ready Knowledge Infrastructure

  Putting documents, data, and algorithms into a form an AI system can reference and reuse, and measuring which specification formats actually help.

• Adaptive Experimental Design

  Updating treatment assignment and subject selection as an experiment runs, so that a limited sample yields a precise estimate of the treatment effect.

• Causal Inference

  Estimating what an intervention causes rather than what correlates with it, and carrying that through to deciding whom to treat.

• Anomaly Detection

  Finding anomalies from how the distribution shifts relative to normal data, for settings where almost no examples of the anomaly are available.

• Weakly Supervised Learning

  Learning classifiers and estimating treatment effects when labels are incomplete, centered on learning from positive and unlabeled data.

• Portfolio Optimization

  Building allocations that account for the uncertainty in the return-prediction model itself as well as in the returns.

• Financial Engineering

  Financial applications outside portfolio selection: time-series analysis, reinforcement learning that controls mean and variance, and audit sampling with statistical guarantees.

• Density-Ratio Estimation

  Estimating the ratio of two densities directly from samples, and using it for anomaly detection, covariate shift adaptation, and causal inference.

• Generalized Riesz Regression

  Estimating the Riesz representer needed for debiased machine learning by minimizing a Bregman divergence, with the Python package genriesz.

• Best-Arm Identification

  Identifying the arm with the highest expected reward from a limited number of trials, under both minimax and Bayes criteria.

• Nonparametric Instrumental Variable Methods

  Estimating causal relationships under endogeneity without assuming a functional form, and giving the resulting predictions coverage guarantees.

Selected Research

These pages describe one paper each: the problem, the method, what was proved and under which conditions, and how it relates to earlier work. They are ordered to follow the topics above.

• AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

  Rather than letting a language model write the economic analysis on its own, the framework combines retrieval, a knowledge graph, and explicit computation with an economic model, so each claim can be traced back to source documents and computed results.

• Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference

  Casts retrieval-augmented action selection as a causal inference problem, reading per-action vector search as nearest neighbor matching and giving a regret decomposition with guarantees.

• Which Algorithm Specification Formats Help Language Models Implement Machine Learning Algorithms?

  Measures how the way an algorithm is written down affects the correctness of the implementation a language model produces, over seven formats and 4,020 generated implementations.

• Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices

  Optimizes both the covariate distribution of the subjects entering the experiment and the treatment assignment probabilities. Selected for an oral presentation at ICML 2024.

• CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression

  Penalizes the difference between two regression models rather than the coefficients themselves, which yields a consistent estimator of the conditional average treatment effect even when neither model is sparse.

• Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy

  Uses the structure of batch policy updates to build an asymptotically normal estimator from the dependent logs that a bandit algorithm collected.

• Learning from Positive and Unlabeled Data with a Selection Bias

  Trains a classifier from positive and unlabeled data when the labeled positives were not drawn uniformly from all positives. Published at ICLR 2019.

• Conformal Predictive Portfolio Selection

  Builds prediction intervals for portfolio returns by conformal prediction and chooses the allocation from those intervals, an approach that works with any underlying return model.

• Sequential Audit Sampling with Statistical Guarantees

  Formulates the practice of extending an audit sample as a sequential test for a finite population under sampling without replacement, with ex ante control of the decision error probabilities.

• Non-negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation

  Finds the overfitting that appears when a deep model estimates a density ratio, and corrects it with a non-negativity adjustment to the empirical loss. Published at ICML 2021.

• A Unified Framework for Debiased Machine Learning: Riesz Representer Fitting under Bregman Divergence

  The main paper behind Generalized Riesz Regression. It states the conditions under which covariate balancing and Neyman orthogonality hold automatically.

• Nearest Neighbor Matching as Least Squares Density Ratio Estimation and Riesz Regression

  Shows that nearest neighbor matching, a standard tool for effect estimation from observational data, can be derived as one implementation of Riesz regression.

• Minimax and Bayes Optimal Best-Arm Identification

  Shows that a single strategy is asymptotically both minimax and Bayes optimal for simple regret in the fixed-budget setting, with upper and lower bounds that match up to the constant.

• The Role of Contextual Information in Best Arm Identification

  Derives the instance-specific sample complexity lower bound when contextual information is available, and gives an algorithm that matches it asymptotically.

• Conformal Prediction for Nonparametric Instrumental Regression

  Gives prediction intervals with distribution-free finite-sample coverage for nonparametric instrumental variable regression, usable with any NPIV estimator.

Publications

The complete list, including work published only in Japanese. Entries marked Details link to the page for that paper.

Working Papers

• Masahiro Kato. "Counterexamples and Sufficient Conditions: Comments on "Optimally-Transported Generalized Method of Moments"" 2026. Details SSRN
• Masahiro Kato and Taka Kato. "Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference" 2026. Details arXiv
• Masahiro Kato and Taka Kato. "Which Algorithm Specification Formats Help Language Models Implement Machine Learning Algorithms?" 2026. Details arXiv
• Masahiro Kato. "AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models" 2026. Details arXiv
• Masahiro Kato. "Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression" 2026. arXiv
• Masahiro Kato. "Covariate Balancing and Riesz Regression Should Be Guided by the Neyman Orthogonal Score in Debiased Machine Learning" 2026. arXiv
• Masahiro Kato and Kei Nakagawa. "Sequential Audit Sampling with Statistical Guarantees" 2026. Details arXiv
• Masahiro Kato. "Conformal Prediction for Nonparametric Instrumental Regression" 2026. Details arXiv
• Takashi Kameyama, Masahiro Kato, Yasuko Hio, Yasushi Takano, and Naoto Minakawa. "Causality Elicitation from Large Language Models" 2026. arXiv
• Masahiro Kato. "genriesz: A Python Package for Automatic Debiased Machine Learning with Generalized Riesz Regression" 2026. Details arXiv
• Masahiro Kato. "A Unified Framework for Debiased Machine Learning: Riesz Representer Fitting under Bregman Divergence" 2026. Details arXiv
• Masahiro Kato. "Causal-Policy Forest for End-to-End Policy Learning" 2025. arXiv
• Masahiro Kato. "Semi-Supervised Treatment Effect Estimation with Unlabeled Covariates for Prediction-Powered Causal Inference" 2025. arXiv
• Masahiro Kato. "A Unified Theory for Causal Inference: Direct Debiased Machine Learning via Bregman-Riesz Regression" 2025. arXiv
• Masahiro Kato. "Bridging the Gap between Empirical Welfare Maximization and Conditional Average Treatment Effect Estimation in Policy Learning" 2025. arXiv Poster
• Masahiro Kato. "Nearest Neighbor Matching as Least Squares Density Ratio Estimation and Riesz Regression" 2025. Details arXiv
• Masahiro Kato. "Direct Debiased Machine Learning via Bregman Divergence Minimization" 2025. arXiv
• Masahiro Kato. "Direct Bias-Correction Term Estimation for Average Treatment Effect Estimation" 2025. arXiv
• Masahiro Kato. "Minimax and Bayes Optimal Best-Arm Identification" 2025. Details arXiv Poster Short version: arXiv:2512.08513
• Masahiro Kato, Kyohei Okumura, Takuya Ishihara, and Toru Kitagawa. "Adaptive Experimental Design for Policy Learning" 2024. arXiv Poster
• Masahiro Kato. "Generalized Neyman Allocation for Locally Minimax Optimal Best-Arm Identification" (under review) 2024. arXiv Poster
• Masahiro Kato. "Debiased Nonparametric Regression for Statistical Inference and Distributionally Robustness" 2024. arXiv
• Masahiro Kato. "Triple/Debiased Lasso for Statistical Inference of Conditional Average Treatment Effects" 2024. arXiv
• Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, and Yutaka Matsuo. "A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees" 2024. arXiv
• Masahiro Kato, Kota Matsui, and Ryo Inokuchi. "Double Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimation" (under review) 2023. arXiv Poster
• Masahiro Kato and Masaaki Imaizumi. "CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression" 2023. Details arXiv Slides Poster
• Masahiro Kato, Shuting Wu, Kodai Kureishi, and Shota Yasui. "Automatic Debiased Learning from Positive, Unlabeled, and Exposure Data" 2023. arXiv
• Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, and Toru Kitagawa. "Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds" 2023. arXiv Poster
• Danielle Cabel, Shonosuke Sugasawa, Masahiro Kato, Kosaku Takanashi, and Kenichiro McAlinn. "Bayesian Spatial Predictive Synthesis" 2022. arXiv
• Masahiro Kato and Masaaki Imaizumi. "Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression" 2022. arXiv
• Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn, and Chao Qin. "Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling" 2021. Revise and Resubmit at Econometrica. arXiv
• Masahiro Kato. "Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability" 2021. arXiv
• Masahiro Kato, Takuya Ishihara, Junya Honda, and Yusuke Narita. "Efficient Adaptive Experimental Design for Average Treatment Effect Estimation" 2020. Revise and Resubmit at JASA. arXiv
• Masahiro Kato, Kei Nakagawa, Kenshi Abe, Tetsuro Morimura, and Kentaro Baba. "Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment" 2020. arXiv
• Masahiro Kato and Yusuke Kaneko. "Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy" 2020. Details arXiv
• Masahiro Kato, Zhenghang Cui, and Yoshihiro Fukuhara. "ATRO: Adversarial Training with a Rejection Option" 2020. arXiv
• Masahiro Kato, Kenshi Abe, Kaito Ariu, and Shota Yasui. "A Practical Guide of Off-Policy Evaluation for Bandit Problems" 2020. arXiv
• Masahiro Kato. "Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales" 2020. arXiv
• Masahiro Kato. "Identifying Different Definitions of Future in the Assessment of Future Economic Conditions: Application of PU Learning and Text Mining" 2019. arXiv
• Masahiro Kato, Liyuan Xu, Gang Niu, and Masashi Sugiyama. "Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data" 2018. arXiv

International Conference Proceedings

• Masahiro Kato. "General Bayesian Policy Learning" In the Conference on Uncertainty in Artificial Intelligence (UAI), 2026. arXiv
• Masahiro Kato. "ScoreMatchingRiesz: Score Matching for Debiased Machine Learning and Policy Path Estimation" In the International Conference on Machine Learning (ICML), 2026. arXiv
• Kiet Q. H. Vo, Siu Lun Chau, Masahiro Kato, Yixin Wang, and Krikamol Muandet. "Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses" In the International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. Proceedings page arXiv
• Masahiro Kato, Fumiaki Kozai, and Ryo Inokuchi. "PUATE: Efficient ATE Estimation from Treated (Positive) and Unlabeled Units" In Advances in Neural Information Processing Systems (NeurIPS), 2025. OpenReview arXiv Poster
• Yuika Shiina*, Masahiro Kato, and Ryo Inokuchi. "Analysis of the Keiki Watchers Survey using Independent Component Analysis and Linear Discriminant Analysis" In the 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF), 2025.
• Masahiro Kato*, Yuki Ikeda, Kentaro Baba, Takashi Imai, and Ryo Inokuchi. "Learning from Double Positive and Unlabeled Data for Potential-Customer Identification" In the 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF), 2025. arXiv
• Masahiro Kato*. "Locally Optimal Fixed-Budget Best Arm Identification in Two-Armed Gaussian Bandits with Unknown Variances" In the 3rd International Conference on Computational and Data Sciences in Economics and Finance (CDEF), 2025. arXiv
• Masahiro Kato* and Shinji Ito. "LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits" In the International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. OpenReview arXiv Poster
• Masahiro Kato*. "Analysis of the Temporal Structure in Economic Condition Assessments" In IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), 2024. IEEE
• Masahiro Kato*, Kentaro Baba, Hibiki Kaibuchi, and Ryo Inokuchi. "Bayesian Portfolio Optimization by Predictive Synthesis" In IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), 2024. IEEE arXiv
• Masahiro Kato*, Akihiro Oga, Wataru Komatsubara, and Ryo Inokuchi. "Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices" In the International Conference on Machine Learning (ICML, Oral 1.5%), 2024. Details PMLR arXiv Slides Poster
• Masahiro Kato*, Masaaki Imaizumi, and Kentaro Minami. "Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics" In the International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. arXiv Poster
• Shota Yasui* and Masahiro Kato* (*Equal contribution). "Learning Classifiers under Delayed Feedback with a Time Window Assumption" In the International Conference on Knowledge Discovery and Data Mining (KDD), 2022. ACM arXiv
• Masahiro Kato*, Masaaki Imaizumi, Kenichiro McAlinn, Shota Yasui, and Haruo Kakehi. "Learning Causal Models from Conditional Moment Restrictions by Importance Weighting" In the International Conference on Learning Representations (ICLR, Spotlight 4% 176/3391), 2022. OpenReview arXiv Poster
• Masahiro Kato*, Kenichiro McAlinn, and Shota Yasui. "The Adaptive Doubly Robust Estimator and a Paradox Concerning Logging Policy" In Advances in Neural Information Processing Systems (NeurIPS), 2021. OpenReview arXiv
• Masahiro Kato* and Takeshi Teshima. "Non-negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation" In the International Conference on Machine Learning (ICML), 2021. Details PMLR arXiv
• Riku Togashi, Masahiro Kato, Mayu Otani, Tetsuya Sakai, and Shin'ichi Satoh. "Scalable Personalised Item Ranking through Parametric Density Estimation" In the Conference on Research and Development in Information Retrieval (SIGIR), 2021. ACM arXiv
• Riku Togashi, Masahiro Kato, Mayu Otani, and Shin'ichi Satoh. "Density-Ratio Based Personalised Ranking from Implicit Feedback" In the Web Conference (WWW), 2021. ACM arXiv
• Masatoshi Uehara*, Masahiro Kato*, and Shota Yasui (*Equal contribution). "Off-Policy Evaluation and Learning for External Validity under a Covariate Shift" In Advances in Neural Information Processing Systems (NeurIPS, Spotlight 3% 280/9054), 2020. NeurIPS arXiv
• Masahiro Kato*, Takeshi Teshima, and Junya Honda. "Learning from Positive and Unlabeled Data with a Selection Bias" In the International Conference on Learning Representations (ICLR), 2019. Details OpenReview

* denotes the first or co-first author.

Journal Articles

• Masahiro Kato and Kaito Ariu. "The Role of Contextual Information in Best Arm Identification" Journal of Machine Learning Research (JMLR) 27(51), 1–61, 2026. Details JMLR arXiv
• Kei Nakagawa, Masahiro Kato, and Mitsuyoshi Imamura. "Subspace regularized principal component analysis using prior exposure information" (accepted) Finance Research Letters, 2026.
• Junpei Komiyama, Kaito Ariu, Masahiro Kato, and Chao Qin. "Rate-Optimal Bayesian Simple Regret in Best Arm Identification" Mathematics of Operations Research 49(3), 1629–1646, 2024. INFORMS arXiv
• Masahiro Kato and Shinji Ito. "Best-of-Both-Worlds Linear Contextual Bandits" Transactions on Machine Learning Research (TMLR), 2024. OpenReview arXiv
• Masahiro Kato. "Riesz Regression As Direct Density Ratio Estimation" (accepted) Finance Research Letters. Project arXiv
• Masahiro Kato and Akari Ohda. "Asymptotically Unbiased Synthetic Control Methods by Moment Matching" (accepted) Journal of Causal Inference. Project arXiv Poster

Domestic Journal Articles

• Elnara Abdullaeva, Takashi Oguchi, Azusa Toriumi, and Masahiro Kato. "Modeling two-vehicle interaction at freeway-on ramp merging section with game theory" SEISAN KENKYU 72(2), 153–158, 2020. Paper

Domestic Conference Proceedings

• 椎名唯圭、加藤真大、井口亮。「独立成分分析とFisherの線形判別による内閣府景気ウォッチャー調査データの分析」言語処理学会 第31回年次大会。 Paper
• 加藤真大、浦川通、田口雄哉、新妻巧朗、田森秀明、羽根田賢和、持橋大地。「線形判別分析のPU学習による朝日歌壇短歌の分析」言語処理学会 第31回年次大会。 Paper
• 中川慧、加藤真大、今村光良。「事前エクスポージャー情報を活用した部分空間正則化付き主成分分析」第35回 人工知能学会 金融情報学研究会（SIG-FIN）。 Paper
• Masahiro Kato. "Conformal Predictive Portfolio Selection" JAFEE 2024 Winter Meeting. Details arXiv
• 井口亮、加藤真大、貝淵響、野田俊也、今泉允聡。「密度比マッチングと勾配コミュニケーションによる異質性を伴う連合学習」第32回 人工知能学会 金融情報学研究会（SIG-FIN）。 Paper
• 馬場健太郎、加藤真大、今井岳。「二重PU学習による潜在的顧客の特定」第32回 人工知能学会 金融情報学研究会（SIG-FIN）。 Paper
• 加藤真大、貝淵響。「ベイジアン予測統合に基づくポートフォリオ選択」第32回 人工知能学会 金融情報学研究会（SIG-FIN）。 Paper
• 加藤真大、浦川通、田口雄哉、新妻巧朗、田森秀明、羽根田賢和、持橋大地。「文埋め込みに基づく朝日歌壇短歌の分析」

Workshop Presentations

• Akira Fukuda, Masahiro Kato, Kenichiro McAlinn, and Kosaku Takanashi. "Bayesian Predictive Synthetic Control Methods" In ICML 2023 Workshop on Counterfactuals in Minds and Machines. Slides
• Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, and Toru Kitagawa. "Fixed-Budget Hypothesis Best Arm Identification: On the Information Loss in Experimental Design" In ICML 2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems. OpenReview Poster
• Masahiro Kato, Kaito Ariu, Masaaki Imaizumi, Masahiro Nomura, and Chao Qin. "Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap" Allied Social Sciences Association (ASSA) 2023 Annual Meeting. arXiv Slides
• Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, and Toru Kitagawa. "Semiparametric Best Arm Identification with Contextual Information" In IBIS 2022. arXiv Poster
• 加藤真大。「経済学と機械学習：因果推論と密度比推定を中心に」統計・機械学習若手シンポジウム 2022。 Slides
• Masahiro Kato. "Recent Findings on Density-Ratio Approaches in Machine Learning" Workshop on Functional Inference and Machine Intelligence (FIMI), 2022.
• Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Shota Yasui, and Haruo Kakehi. "Learning Causal Relationships from Conditional Moment Conditions by Importance Weighting" In NeurIPS 2021 Workshop on Machine Learning meets Econometrics. arXiv
• Masahiro Kato, Kei Nakagawa, Kenshi Abe, and Tetsuro Morimura. "Direct Expected Quadratic Utility Maximization for Mean-Variance Controlled Reinforcement Learning" In NeurIPS 2021 Workshop on Deep Reinforcement Learning. arXiv Poster
• 加藤真大。「効率的な因果推論と意思決定のための実験計画において異質性が果たす役割」統計関連学会連合大会 2021。 Slides
• Masahiro Kato, Shota Yasui, and Kenichiro McAlinn. "The Adaptive Doubly Robust Estimator for Policy Evaluation in Adaptive Experiments" In ICML 2021 Workshop on The Neglected Assumptions In Causal Inference. arXiv
• Masahiro Kato, Takuya Ishihara, Junya Honda, and Yusuke Narita. "Adaptive Experimental Design for Efficient Treatment Effect Estimation" In NeurIPS 2020 Workshop on Causal Discovery & Causality-Inspired Machine Learning.
• 加藤真大。「平均処置効果の推定のための適応的実験計画」慶應計量経済学ワークショップ 2020。 Slides

Other

• Masahiro Kato. "A Note on Doubly Robust Estimator in Regression Discontinuity Designs" Technical note. arXiv
• Masahiro Kato, Kei Nakagawa, Kenshi Abe, Tetsuro Morimura, and Kentaro Baba. "Direct Expected Quadratic Utility Maximization for Mean-Variance Controlled Reinforcement Learning" In the IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr). Accepted but not included in the proceedings. arXiv

Links

• Google Scholar
• GitHub
• LinkedIn
• researchmap
• Software (in Japanese)
• Books (in Japanese)
• Articles (in Japanese)
• Media coverage (in Japanese)

For research inquiries, write to mkato-csecon@g.ecc.u-tokyo.ac.jp. The contact form is in Japanese.