3 papers
cs.LG2026
SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography
Shunta Nonaga, Koji Tabata, Junya Honda +3
Computed Tomography (CT) is indispensable in clinical diagnostics, yet minimizing radiation dose without compromising image quality remains a critical challenge. Conventional low-d…
stat.ML2025
Efficient Adaptive Experimental Design for Average Treatment Effect Estimation
Masahiro Kato, Takuya Ishihara, Junya Honda +1
We study how to efficiently estimate average treatment effects (ATEs) using adaptive experiments. In adaptive experiments, experimenters sequentially assign treatments to experimen…
cs.LG2024
A General Recipe for the Analysis of Randomized Multi-Armed Bandit Algorithms
Dorian Baudry, Kazuya Suzuki, Junya Honda
In this paper we propose a general methodology to derive regret bounds for randomized multi-armed bandit algorithms. It consists in checking a set of sufficient conditions on the s…