# Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling

arXiv: https://arxiv.org/abs/1602.07415 · HTML: https://mlsanity.com/paper/1602.07415/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2016.

## Built on by (most cited first, 5 of 5)

- [Semantic Probabilistic Control of Language Models](https://mlsanity.com/paper/2505.01954/) (2025)
- [A fast asynchronous MCMC sampler for sparse Bayesian inference](https://mlsanity.com/paper/2108.06446/) (2021)
- [Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds](https://mlsanity.com/paper/2111.07372/) (2021)
- [A statistical perspective on algorithm unrolling models for inverse problems](https://mlsanity.com/paper/2311.06395/) (2023)
- [Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Scheme](https://mlsanity.com/paper/2408.12888/) (2024)

## Abstract (arXiv)

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.