Junpei Komiyama

activity

20152026

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

70 citations · 161 across the 37 of their papers we have counts for

collaborators

Showing 2025 · stat.MLShow all

3 papers · 2 filters

stat.ML2025

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 $K$ arms under a limited sampling budget. This pro…

stat.ML2025

Best-of- $\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling

Junpei Komiyama, Daisuke Oba, Masafumi Oyamada

We study best-of- $N$ for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit $N \to \infty$ , which we denote as \boinf…

stat.ML2025

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 $K$ arms, and the goal of the forecaster is to maximize the cumulative reward…

Rate-optimal Design for Anytime Best Arm Identification

Best-of-∞ -- Asymptotic Performance of Test-Time LLM Ensembling

High-dimensional Nonparametric Contextual Bandit Problem

Best-of- $\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling