arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.12936stat.MLcs.LGmath.STstat.TH
收藏

隐马尔可夫模型参数学习的基本极限

Fundamental limits for learning hidden Markov model parameters

Kweku Abraham, Zacharie Naulet, Elisabeth Gassiat

摘要:

我们研究了可学习和不可学习的隐马尔可夫模型(HMM)之间的边界。Hysteresis是一种灵活的工具,用于聚类来自未知群体的相关数据。模型参数被称为是完全可识别的(标签切换),没有任何建模假设的人口的分布,只要集群是不同的,隐藏的链是遍历满秩的过渡矩阵。在这些条件中的任何一个都失败的极限中,通常不可能识别参数。对于一个有两个隐藏状态的链,我们证明了非渐近极大极小的上界和下界,匹配常数,表现出阈值的参数变得可学习。我们还提供了一个上限的相对熵率的参数在附近的不可学习的区域,可能有兴趣在自己。

英文摘要:

We study the frontier between learnable and unlearnable hidden Markov models (HMMs). HMMs are flexible tools for clustering dependent data coming from unknown populations. The model parameters are known to be fully identifiable (up to label-switching) without any modeling assumption on the distributions of the populations as soon as the clusters are distinct and the hidden chain is ergodic with a full rank transition matrix. In the limit as any one of these conditions fails, it becomes impossible in general to identify parameters. For a chain with two hidden states we prove nonasymptotic minimax upper and lower bounds, matching up to constants, which exhibit thresholds at which the parameters become learnable. We also provide an upper bound on the relative entropy rate for parameters in a neighbourhood of the unlearnable region which may have interest in itself.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑