12 citations · 50 across the 23 of their papers we have counts for
23 papers
Asymptotically Unbiased Synthetic Control Methods by Moment Matching
Masahiro Kato, Akari Ohda
Synthetic Control Methods (SCMs) have become a fundamental tool for comparative case studies. The core idea behind SCMs is to estimate treatment effects by predicting counterfactua…
Automatic Debiased Learning from Positive, Unlabeled, and Exposure Data
Masahiro Kato, Shuting Wu, Kodai Kureishi +1
We address the issue of binary classification from positive and unlabeled data (PU classification) with a selection bias in the positive data. During the observation process, (i) a…
Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds
Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara +1
We investigate the problem of fixed-budget best arm identification (BAI) for minimizing expected simple regret. In an adaptive experiment, a decision maker draws one of multiple tr…
Best Arm Identification with Contextual Information under a Small Gap
Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara +1
We study the best-arm identification (BAI) problem with a fixed budget and contextual (covariate) information. In each round of an adaptive experiment, after observing contextual i…
Bayesian Spatial Predictive Synthesis
Danielle Cabel, Shonosuke Sugasawa, Masahiro Kato +2
Due to spatial dependence -- often characterized as complex and non-linear -- model misspecification is a prevalent and critical issue in spatial data analysis and prediction. As t…
Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression
Masahiro Kato, Masaaki Imaizumi
We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models. As the development of machine learning f…
Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics
Masahiro Kato, Masaaki Imaizumi, Kentaro Minami
This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ra…
Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap
Masahiro Kato, Kaito Ariu, Masaaki Imaizumi +2
We consider fixed-budget best-arm identification in two-armed Gaussian bandit problems. One of the longstanding open questions is the existence of an optimal strategy under which t…
Rate-optimal Bayesian Simple Regret in Best Arm Identification
Junpei Komiyama, Kaito Ariu, Masahiro Kato +1
We consider best arm identification in the multi-armed bandit problem. Assuming certain continuity conditions of the prior, we characterize the rate of the Bayesian simple regret.…
Learning Causal Models from Conditional Moment Restrictions by Importance Weighting
Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn +2
We consider learning causal relationships under conditional moment restrictions. Unlike causal inference under unconditional moment restrictions, conditional moment restrictions po…
Scalable Personalised Item Ranking through Parametric Density Estimation
Riku Togashi, Masahiro Kato, Mayu Otani +2
Learning from implicit feedback is challenging because of the difficult nature of the one-class problem: we can observe only positive examples. Most conventional methods use a pair…
Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability
Masahiro Kato
Adaptive experiments, including efficient average treatment effect estimation and multi-armed bandit algorithms, have garnered attention in various applications, such as social exp…
Density-Ratio Based Personalised Ranking from Implicit Feedback
Riku Togashi, Masahiro Kato, Mayu Otani +1
Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones. Most conventional methods cope with this issue by adopti…
ATRO: Adversarial Training with a Rejection Option
Masahiro Kato, Zhenghang Cui, Yoshihiro Fukuhara
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algor…
Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy
Masahiro Kato, Yusuke Kaneko
The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates t…
A Practical Guide of Off-Policy Evaluation for Bandit Problems
Masahiro Kato, Kenshi Abe, Kaito Ariu +1
Off-policy evaluation (OPE) is the problem of estimating the value of a target policy from samples obtained via different policies. Recently, applying OPE methods for bandit proble…
The Adaptive Doubly Robust Estimator for Policy Evaluation in Adaptive Experiments and a Paradox Concerning Logging Policy
Masahiro Kato, Shota Yasui, Kenichiro McAlinn
The doubly robust (DR) estimator, which consists of two nuisance parameters, the conditional mean outcome and the logging policy (the probability of choosing an action), is crucial…
Learning Classifiers under Delayed Feedback with a Time Window Assumption
Masahiro Kato, Shota Yasui
We consider training a binary classifier under delayed feedback (\emph{DF learning}). For example, in the conversion prediction in online ads, we initially receive negative samples…
Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales
Masahiro Kato
This study addresses the problem of off-policy evaluation (OPE) from dependent samples obtained via the bandit algorithm. The goal of OPE is to evaluate a new policy using historic…
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
Masahiro Kato, Takeshi Teshima
Density ratio estimation (DRE) is at the core of various machine learning tasks such as anomaly detection and domain adaptation. In existing studies on DRE, methods based on Bregma…
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
Masahiro Kato, Masatoshi Uehara, Shota Yasui
We consider evaluating and training a new policy for the evaluation data by using the historical data obtained from a different policy. The goal of off-policy evaluation (OPE) is t…
Identifying Different Definitions of Future in the Assessment of Future Economic Conditions: Application of PU Learning and Text Mining
Masahiro Kato
The Economy Watcher Survey, which is a market survey published by the Japanese government, contains \emph{assessments of current and future economic conditions} by people from vari…
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data
Masahiro Kato, Liyuan Xu, Gang Niu +1
We consider a problem of learning a binary classifier only from positive data and unlabeled data (PU learning) and estimating the class-prior in unlabeled data under the case-contr…