[1705.09236] Asynchronous Parallel Bayesian Optimisation via Thompson Sampling

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.

Asynchronous Parallel Bayesian Optimisation via Thompson Sampling Kirthevasan Kandasamy \ , Akshay Krishnamurthy [ , Jeff Schneider \ , Barnabás Póczos \ \ [ Carnegie Mellon University, University of Massachusetts, Amherst {kandasamy, schneide, bapoczos}@cs.cmu.edu, akshay@cs.umass.edu arXiv:1705.09236v1 [stat.ML] 25 May 2017…

related reading

• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [2602.17616] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMsarxiv.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• Is Frontier Asynchronous RL Solved? — Luke J. Huangluk-huang.github.io
• Fast Inference from Transformers via Speculative Decodingarxiv.org
• An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
• [2109.14412] Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classificationar5iv.labs.arxiv.org
• A Gallery of Methods Beyond RL — Part I: Sampling Methodsshengyu-feng.github.io
• A System for Massively Parallel Hyperparameter Tuningarxiv.org
• arxiv.org/pdf/1805.08522arxiv.org
• [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
• Bayes-Optimal Strategiesemergentmind.com