70 citations · 161 across the 37 of their papers we have counts for
19 papers · 1 filter
Rethinking Successive Rejects Algorithms
Mohamed Khair, Junpei Komiyama
In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a simple fixed-budget best-arm i…
Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis
Harsh Shrivastava, Yuta Kawakami, Junpei Komiyama +1
This paper studies the problem of identifying the treatment that maximizes the expected natural direct potential outcome (NDPO), which captures the potential outcome of an interven…
Reliable Chain-of-Thought via Prefix Consistency
Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar +1
Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time techn…
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
Hirofumi Ota, Naoto Iwase, Yuki Ichihara +2
Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challeng…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…
Rate-optimal Design for Anytime Best Arm Identification
Junpei Komiyama, Kyoungseok Jang, Junya Honda
We consider the best arm identification problem, where the goal is to identify the arm with the highest mean reward from a set of arms under a limited sampling budget. This pro…
Best-of- -- Asymptotic Performance of Test-Time LLM Ensembling
Junpei Komiyama, Daisuke Oba, Masafumi Oyamada
We study best-of- for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit , which we denote as \boinf…
High-dimensional Nonparametric Contextual Bandit Problem
Shogo Iwazaki, Junpei Komiyama, Masaaki Imaizumi
We consider the kernelized contextual bandit problem with a large feature space. This problem involves arms, and the goal of the forecaster is to maximize the cumulative reward…
Fixed Confidence Best Arm Identification in the Bayesian Setting
Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki
We consider the fixed-confidence best arm identification (FC-BAI) problem in the Bayesian setting. This problem aims to find the arm of the largest mean with a fixed confidence lev…
Replicability is Asymptotically Free in Multi-armed Bandits
Junpei Komiyama, Shinji Ito, Yuichi Yoshida +1
We consider a replicable stochastic multi-armed bandit algorithm that ensures, with high probability, that the algorithm's sequence of actions is not affected by the randomness inh…
High-dimensional Contextual Bandit Problem without Sparsity
Junpei Komiyama, Masaaki Imaizumi
In this research, we investigate the high-dimensional linear contextual bandit problem where the number of features is greater than the budget , or it may even be infinite.…
Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
Junpei Komiyama, Taira Tsuchiya, Junya Honda
We consider the fixed-budget best arm identification problem where the goal is to find the arm of the largest mean with a fixed number of samples. It is known that the probability…
Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification
Junpei Komiyama
We consider the fixed-budget best arm identification problem with rewards following normal distributions. In this problem, the forecaster is given arms (or treatments) and …
Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits
Junpei Komiyama, Edouard Fouché, Junya Honda
We consider nonstationary multi-armed bandit problems where the model parameters of the arms change over time. We introduce the adaptive resetting bandit (ADR-bandit), a bandit alg…
Two-stage Algorithm for Fairness-aware Machine Learning
Junpei Komiyama, Hajime Shimao
Algorithmic decision making process now affects many aspects of our lives. Standard tools for machine learning, such as classification and regression, are subject to the bias in da…
Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm
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. The hard…
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the…
Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
Junpei Komiyama, Junya Honda, Hisashi Kashima +1
We study the -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. We int…
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesi…