Kernel Recursive ABC: Point Estimation with Intractable Likelihood

Abstract

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.

Cite

Text

Kajihara et al. "Kernel Recursive ABC: Point Estimation with Intractable Likelihood." International Conference on Machine Learning, 2018.

Markdown

[Kajihara et al. "Kernel Recursive ABC: Point Estimation with Intractable Likelihood." International Conference on Machine Learning, 2018.](https://mlanthology.org/icml/2018/kajihara2018icml-kernel/)

BibTeX

@inproceedings{kajihara2018icml-kernel,
  title     = {{Kernel Recursive ABC: Point Estimation with Intractable Likelihood}},
  author    = {Kajihara, Takafumi and Kanagawa, Motonobu and Yamazaki, Keisuke and Fukumizu, Kenji},
  booktitle = {International Conference on Machine Learning},
  year      = {2018},
  pages     = {2400-2409},
  volume    = {80},
  url       = {https://mlanthology.org/icml/2018/kajihara2018icml-kernel/}
}