De Sa Christopher, Olukotun Kunle, Ré Christopher
Department of Electrical Engineering, Stanford University, Stanford, CA 94309.
Department of Computer Science, Stanford University, Stanford, CA 94309.
JMLR Workshop Conf Proc. 2016;48:1567-1576.
Gibbs sampling is a Markov chain Monte Carlo technique commonly used for estimating marginal distributions. To speed up Gibbs sampling, there has recently been interest in parallelizing it by executing asynchronously. While empirical results suggest that many models can be efficiently sampled asynchronously, traditional Markov chain analysis does not apply to the asynchronous case, and thus asynchronous Gibbs sampling is poorly understood. In this paper, we derive a better understanding of the two main challenges of asynchronous Gibbs: bias and mixing time. We show experimentally that our theoretical results match practical outcomes.
吉布斯采样是一种马尔可夫链蒙特卡罗技术，常用于估计边际分布。为了加速吉布斯采样，最近人们对通过异步执行来实现其并行化产生了兴趣。虽然实证结果表明许多模型可以通过异步方式有效地进行采样，但传统的马尔可夫链分析不适用于异步情况，因此对异步吉布斯采样的理解还很不足。在本文中，我们对异步吉布斯采样的两个主要挑战：偏差和混合时间，有了更好的理解。我们通过实验表明，我们的理论结果与实际结果相符。
