arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08404stat.ML
收藏

核递归ABC:似然不可解的点估计

Kernel Recursive ABC: Point Estimation with Intractable Likelihood

Takafumi Kajihara, Motonobu Kanagawa, Keisuke Yamazaki, Kenji Fukumizu

摘要:

提出了一种新的基于模拟器的统计模型的参数估计方法。我们提出的方法涉及递归应用核ABC和内核放牧相同的观测数据。我们提供了一个理论上的解释,为什么这种方法的工作原理,显示(人口设置),在一定的假设下,用这种方法获得的点估计收敛到真正的参数,递归的收益。我们已经进行了各种数值实验,包括参数估计的真实世界的行人流模拟器,并表明,在大多数情况下,我们的方法优于现有的方法。

英文摘要:

We propose a novel approach to parameter estimation for simulator-based statistical models with intractable likelihood. Our proposed method involves recursive application of kernel ABC and kernel herding to the same observed data. We provide a theoretical explanation regarding why the approach works, showing (for the population setting) that, under a certain assumption, point estimates obtained with this method converge to the true parameter, as recursion proceeds. We have conducted a variety of numerical experiments, including parameter estimation for a real-world pedestrian flow simulator, and show that in most cases our method outperforms existing approaches.

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。

↑