tfp.mcmc：为现代硬件打造的现代马尔可夫链蒙特卡罗工具
统计计算
2020-02-05 v1 编程语言
机器学习
摘要
马尔可夫链蒙特卡罗（MCMC）被广泛认为是 20 世纪最重要的算法之一。它仅使用未归一化概率函数即可保证渐近收敛、稳定性以及估计量方差界，这使其对概率编程不可或缺。本文介绍 TensorFlow Probability MCMC 工具包，并讨论促使其设计的一些考量。
引用
@article{arxiv.2002.01184,
title = {tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware},
author = {Junpeng Lao and Christopher Suter and Ian Langmore and Cyril Chimisov and Ashish Saxena and Pavel Sountsov and Dave Moore and Rif A. Saurous and Matthew D. Hoffman and Joshua V. Dillon},
journal= {arXiv preprint arXiv:2002.01184},
year = {2020}
}
备注
Based on extended abstract submitted to PROBPROG 2020