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 1807.01346stat.COmath.PRstat.ME
收藏

基于$L_2$范数的序贯蒙特卡洛有限样本界与自适应路径选择

Finite Sample Bounds for Sequential Monte Carlo and Adaptive Path Selection Using the $L_2$ Norm

Joe Marion, Joseph Mathews, Scott C. Schmidler

AI总结:

本文基于$L_2$距离与马尔可夫核混合时间,首次在不要求重要性权重上界的条件下证明了SMC的有限样本误差界,并据此提出满足理论保证的修改数据退火算法,实现自适应且近乎最优的分布序列选择。

摘要:

我们利用插值分布之间的$L_2$距离与马尔可夫核的混合时间,证明了静态空间上序贯蒙特卡洛(SMC)有限样本误差的一个界。该结果的独特之处在于,它是第一个不要求重要性权重存在上界的SMC有限样本收敛结果。利用这一界,我们表明仔细选择插值分布可以显著改善算法的计算复杂度。该结果也为文献中常用的基于相对有效样本量的SMC分布自适应选择提供了理论依据,并且我们建立了保证自适应SMC方法近似精度的条件。我们证明常用的数据退火方法无法满足这些条件,并引入了一种修改后的数据退火算法,在该算法下我们的保证确实成立。随后,我们通过实验证明,对于现实示例,该过程能够以自动方式提供近乎最优的分布序列。

英文摘要:

We prove a bound on the finite sample error of sequential Monte Carlo (SMC) on static spaces using the $L_2$ distance between interpolating distributions and the mixing times of Markov kernels. This result is unique in that it is the first finite sample convergence result for SMC that does not require an upper bound on the importance weights. Using this bound we show that careful selection of the interpolating distributions can lead to substantial improvements in the computational complexity of the algorithm. This result also justifies the adaptive selection of SMC distributions using the relative effective sample size commonly used in the literature, and we establish conditions guaranteeing the approximation accuracy of the adaptive SMC approach. We show that the commonly used data tempering approach fails to satisfy these conditions, and introduce a modified data tempering algorithm under which our guarantees do hold. We then demonstrate empirically that this procedure provides nearly-optimal sequences of distributions in an automatic fashion for realistic examples.

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。

↑