跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24988 · v1

Variance-Adaptive Upper Confidence Bounds for Multi-Armed Bandits with Kaplan--Meier Survival Estimation

首次提交 2026-11-18 13:42
版本更新 2026-11-18 13:42
雷达观测 2026-11-21 12:19
arXiv ↗PDF ↗

摘要

We study the stochastic multi-armed bandit problem in which the reward associated with each arm is the survival probability at a pre-specified time horizon, and the observed outcome is a right-censored time-to-event variable. Standard bandit algorithms face delayed and partial observations in this setting. Prior adaptations for the Kaplan--Meier (KM) estimator rely on Hoeffding-type bounds that ignore the inherent heteroscedasticity of continuous survival processes. To bridge this gap, we propose KM-UCB, a variance-adaptive policy that unites continuous-time survival analysis with discrete sequential decision-making. By leveraging martingale theory and continuous influence functions, we derive a fixed-cohort empirical Bernstein bound parameterized by Greenwood's variance formula. For realtime allocation, we retain the Greenwood index and use a survival bound from completed records to review the recommended arm. Under catch-up reporting, the policy has logarithmic expected regret with an arm-specific variance term in the exploration bound. We evaluate the original policy in a dual-layer delayed simulation and a retrospective replay of breast cancer trial data, and evaluate the correction in a separate paired simulation.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 13:42 · 最新观测版本

Variance-Adaptive Upper Confidence Bounds for Multi-Armed Bandits with Kaplan--Meier Survival Estimation

We study the stochastic multi-armed bandit problem in which the reward associated with each arm is the survival probability at a pre-specified time horizon, and the observed outcome is a right-censored time-to-event variable. Standard bandit algorithms face delayed and partial observations in this setting. Prior adaptations for the Kaplan--Meier (KM) estimator rely on Hoeffding-type bounds that ignore the inherent heteroscedasticity of continuous survival processes. To bridge this gap, we propose KM-UCB, a variance-adaptive policy that unites continuous-time survival analysis with discrete sequential decision-making. By leveraging martingale theory and continuous influence functions, we derive a fixed-cohort empirical Bernstein bound parameterized by Greenwood's variance formula. For realtime allocation, we retain the Greenwood index and use a survival bound from completed records to review the recommended arm. Under catch-up reporting, the policy has logarithmic expected regret with an arm-specific variance term in the exploration bound. We evaluate the original policy in a dual-layer delayed simulation and a retrospective replay of breast cancer trial data, and evaluate the correction in a separate paired simulation.

查看此版本解读 →查看此版本原文 ↗