发表机构
Okinawa Institute of Science and Technology(冲绳科学技术大学院大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
该研究针对从单条平稳轨迹估计马尔可夫链平均混合时间的样本复杂度,建立了几乎匹配的逆界,明确了估计不可能的情形,与现有可达性界匹配,为该估计提供了几乎紧密的 PAC 保证。
AI 中文摘要
我们针对从单条平稳轨迹估计马尔可夫链平均混合时间的样本复杂度,建立了几乎匹配的 converse 界(逆界)。与最坏情况混合时间(其在所有初始状态上最大化到平稳状态的总变差距离)不同,平均混合时间是在平稳分布下对该距离取平均,因此可能显著更小。我们的逆界明确了估计不可能的情形,且在对数因子范围内与现有 achievability 界(可达性界)的关键依赖关系相匹配。这些界共同为估计平均混合时间提供了几乎紧密的 PAC 保证。
英文摘要
We establish nearly-matching converse bounds on the sample complexity of estimating the average mixing time of a Markov chain from a single stationary trajectory. Unlike the worst-case mixing time, which maximises the total-variation distance to stationarity over all initial states, the average mixing time averages this distance under the stationary distribution and can therefore be substantially smaller. Our converse bounds establish when estimation is impossible, and match the key dependencies in existing achievability bounds, up to logarithmic factors. Together, these bounds provide nearly-tight PAC guarantees for estimating the average mixing time.