Search Results for author: Junpei Komiyama

Found 23 papers, 9 papers with code

Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays

1 code implementation2 Jun 2015 Junpei Komiyama, Junya Honda, Hiroshi Nakagawa

Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the standard single-play MAB problem.

Thompson Sampling

Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem

1 code implementation8 Jun 2015 Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms.

Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring

no code implementations NeurIPS 2015 Junpei Komiyama, Junya Honda, Hiroshi Nakagawa

To show the optimality of PM-DMED with respect to the regret bound, we slightly modify the algorithm by introducing a hinge function (PM-DMED-Hinge).

Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm

no code implementations5 May 2016 Junpei Komiyama, Junya Honda, Hiroshi Nakagawa

We study the K-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms.

Two-stage Algorithm for Fairness-aware Machine Learning

no code implementations13 Oct 2017 Junpei Komiyama, Hajime Shimao

Here, we study a fair machine learning algorithm that avoids such a disparate impact when making a decision.

BIG-bench Machine Learning Decision Making +4

Position-based Multiple-play Bandit Problem with Unknown Position Bias

no code implementations NeurIPS 2017 Junpei Komiyama, Junya Honda, Akiko Takeda

Motivated by online advertising, we study a multiple-play multi-armed bandit problem with position bias that involves several slots and the latter slots yield fewer rewards.

Position

Comparing Fairness Criteria Based on Social Outcome

no code implementations13 Jun 2018 Junpei Komiyama, Hajime Shimao

Fairness in algorithmic decision-making processes is attracting increasing concern.

Decision Making Fairness

Nonconvex Optimization for Regression with Fairness Constraints

1 code implementation ICML 2018 Junpei Komiyama, Akiko Takeda, Junya Honda, Hajime Shimao

However, a fairness level as a constraint induces a nonconvexity of the feasible region, which disables the use of an off-the-shelf convex optimizer.

Attribute Fairness +1

A Simple Way to Deal with Cherry-picking

no code implementations11 Oct 2018 Junpei Komiyama, Takanori Maehara

Statistical hypothesis testing serves as statistical evidence for scientific innovation.

Selection bias Two-sample testing

A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy

no code implementations2 Oct 2019 Kei Nakagawa, Masaya Abe, Junpei Komiyama

Stock return predictability is an important research theme as it reflects our economic and social organization, and significant efforts are made to explain the dynamism therein.

BIG-bench Machine Learning Decision Making +1

On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach

1 code implementation2 Oct 2020 Junpei Komiyama, Shunya Noda

Even a marginal imbalance in the population ratio frequently results in perpetual underestimation.

Controlling False Discovery Rates under Cross-Sectional Correlations

no code implementations15 Feb 2021 Junpei Komiyama, Masaya Abe, Kei Nakagawa, Kenichiro McAlinn

We achieve superior statistical power to existing methods and prove that the false discovery rate is controlled.

Time Series Time Series Analysis

Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits

1 code implementation23 Jul 2021 Junpei Komiyama, Edouard Fouché, Junya Honda

We demonstrate that ADR-bandit has nearly optimal performance when abrupt or gradual changes occur in a coordinated manner that we call global changes.

Multi-Armed Bandits

Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling

no code implementations16 Sep 2021 Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn, Chao Qin

We consider the "policy choice" problem -- otherwise known as best arm identification in the bandit literature -- proposed by Kasy and Sautmann (2021) for adaptive experimental design.

Decision Making Experimental Design

Deviation-Based Learning: Training Recommender Systems Using Informed User Choice

1 code implementation20 Sep 2021 Junpei Komiyama, Shunya Noda

This paper proposes a new approach to training recommender systems called deviation-based learning.

Recommendation Systems

Rate-optimal Bayesian Simple Regret in Best Arm Identification

1 code implementation18 Nov 2021 Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin

We consider best arm identification in the multi-armed bandit problem.

Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification

no code implementations10 Feb 2022 Junpei Komiyama

The algorithm's performance is measured by the simple regret, that is, the quality of the estimated best arm.

Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search

1 code implementation14 Feb 2022 Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki

Constructing a good search tree representation significantly boosts the performance of the proposed method.

Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification

1 code implementation9 Jun 2022 Junpei Komiyama, Taira Tsuchiya, Junya Honda

We introduce two rates, $R^{\mathrm{go}}$ and $R^{\mathrm{go}}_{\infty}$, corresponding to lower bounds on the probability of misidentification, each of which is associated with a proposed algorithm.

Strategic Choices of Migrants and Smugglers in the Central Mediterranean Sea

no code implementations10 Jul 2022 Katherine Hoffmann Pham, Junpei Komiyama

The sea crossing from Libya to Italy is one of the world's most dangerous and politically contentious migration routes, and yet over half a million people have attempted the crossing since 2014.

Learning Fair Division from Bandit Feedback

no code implementations15 Nov 2023 Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki

This work addresses learning online fair division under uncertainty, where a central planner sequentially allocates items without precise knowledge of agents' values or utilities.

Replicability is Asymptotically Free in Multi-armed Bandits

no code implementations12 Feb 2024 Junpei Komiyama, Shinji Ito, Yuichi Yoshida, Souta Koshino

For the analysis of these algorithms, we propose a principled approach to limiting the probability of nonreplication.

Decision Making Multi-Armed Bandits

Fixed Confidence Best Arm Identification in the Bayesian Setting

no code implementations16 Feb 2024 Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki

This problem aims to find the arm of the largest mean with a fixed confidence level when the bandit model has been sampled from the known prior.

Cannot find the paper you are looking for? You can Submit a new open access paper.