# Asynchronous Parallel Bayesian Optimisation via Thompson Sampling

arXiv: https://arxiv.org/abs/1705.09236 · HTML: https://mlsanity.com/paper/1705.09236/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 7 of 7)

- [Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale](https://mlsanity.com/paper/2201.06834/) (2022)
- [Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks](https://mlsanity.com/paper/2106.09884/) (2021)
- [Generative Bayesian Optimization: Generative Models as Acquisition Functions](https://mlsanity.com/paper/2510.25240/) (2025)
- [Optimal Initialization of Batch Bayesian Optimization](https://mlsanity.com/paper/2404.17997/) (2024)
- [Scalable3-BO: Big Data meets HPC - A scalable asynchronous parallel high-dimensional Bayesian optimization framework on supercomputers](https://mlsanity.com/paper/2108.05969/) (2021)
- [Thompson Sampling in Function Spaces via Neural Operators](https://mlsanity.com/paper/2506.21894/) (2025)
- [Taking the GP Out of the Loop](https://mlsanity.com/paper/2506.12818/) (2025)

## Abstract (arXiv)

We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a direct application of the sequential Thompson sampling algorithm in either synchronous or asynchronous parallel settings yields a surprisingly powerful result: making n evaluations distributed among M workers is essentially equivalent to performing n evaluations in sequence. Further, by modeling the time taken to complete a function evaluation, we show that, under a time constraint, asynchronously parallel TS achieves asymptotically lower regret than both the synchronous and sequential versions. These results are complemented by an experimental analysis, showing that asynchronous TS outperforms a suite of existing parallel BO algorithms in simulations and in a hyper-parameter tuning application in convolutional neural networks. In addition to these, the proposed procedure is conceptually and computationally much simpler than existing work for parallel BO.