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 2102.05743cs.DCstat.ML
收藏

隐马尔可夫模型中推理的时间离散化

Temporal Parallelization of Inference in Hidden Markov Models

Sakira Hassan, Simo Särkkä, Ángel F. García-Fernández

摘要:

本文提出了隐马尔可夫模型(HMRM)的并行推理算法。特别是,我们提出了并行向后-向前型滤波和平滑算法以及并行维特比型最大后验概率(MAP)算法。我们定义关联元素和运营商提出这些推理问题的并行前缀和计算的总和产品和最大产品的算法和并行化,使用并行扫描算法。所提出的算法的优点是,它们是计算效率的HMM推理问题与长时间的视野。我们经验比较所提出的方法的性能,经典的方法在一个高度并行的图形处理单元(GPU)。

英文摘要:

This paper presents algorithms for parallelization of inference in hidden Markov models (HMMs). In particular, we propose parallel backward-forward type of filtering and smoothing algorithm as well as parallel Viterbi-type maximum-a-posteriori (MAP) algorithm. We define associative elements and operators to pose these inference problems as parallel-prefix-sum computations in sum-product and max-product algorithms and parallelize them using parallel-scan algorithms. The advantage of the proposed algorithms is that they are computationally efficient in HMM inference problems with long time horizons. We empirically compare the performance of the proposed methods to classical methods on a highly parallel graphical processing unit (GPU).

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。

↑