隐马尔可夫模型全变差距离的计算
On Computing the Total Variation Distance of Hidden Markov Models
摘要:
我们证明了结果的可判定性和计算的总变异距离(相当于,$L_1$距离)的隐马尔可夫模型(相当于,标记马尔可夫链)的复杂性。这个距离度量了两个隐马尔可夫模型诱导的单词分布之间的差异。主要结果是:(1)距离是否大于给定阈值是不可判定的;(2)近似是PSPACE中的#P-hard。
英文摘要:
We prove results on the decidability and complexity of computing the total variation distance (equivalently, the $L_1$-distance) of hidden Markov models (equivalently, labelled Markov chains). This distance measures the difference between the distributions on words that two hidden Markov models induce. The main results are: (1) it is undecidable whether the distance is greater than a given threshold; (2) approximation is #P-hard and in PSPACE.
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。