# Adaptive Rate of Convergence of Thompson Sampling for Gaussian Process Optimization

arXiv: https://arxiv.org/abs/1705.06808 · HTML: https://mlsanity.com/paper/1705.06808/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2017.

## Built on by (most cited first, 9 of 9)

- [Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2204.05944/) (2022)
- [Discovering Diverse Athletic Jumping Strategies](https://mlsanity.com/paper/2105.00371/) (2021)
- [Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2110.06980/) (2021)
- [Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation](https://mlsanity.com/paper/2307.13371/) (2023)
- [ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine](https://mlsanity.com/paper/2111.13415/) (2021)
- [An Analysis of Reinforcement Learning for Malaria Control](https://mlsanity.com/paper/2107.08988/) (2021)
- [Learning to Act: Novel Integration of Algorithms and Models for Epidemic Preparedness](https://mlsanity.com/paper/2210.02055/) (2022)
- [Predictive Modeling through Hyper-Bayesian Optimization](https://mlsanity.com/paper/2308.00285/) (2023)
- [Nonparametric Bayesian Optimization for General Rewards](https://mlsanity.com/paper/2602.07411/) (2026)

## Abstract (arXiv)

We consider the problem of global optimization of a function over a continuous domain. In our setup, we can evaluate the function sequentially at points of our choice and the evaluations are noisy. We frame it as a continuum-armed bandit problem with a Gaussian Process prior on the function. In this regime, most algorithms have been developed to minimize some form of regret. In this paper, we study the convergence of the sequential point xt to the global optimizer x^* for the Thompson Sampling approach. Under some assumptions and regularity conditions, we prove concentration bounds for xt where the probability that xt is bounded away from x^* decays exponentially fast in t. Moreover, the result allows us to derive adaptive convergence rates depending on the function structure.