# Provable Accelerated Bayesian Optimization with Knowledge Transfer

arXiv: https://arxiv.org/abs/2511.03125 · HTML: https://mlsanity.com/paper/2511.03125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [On Kernelized Multi-armed Bandits](https://mlsanity.com/paper/1704.00445/) (2017)
- [A System for Massively Parallel Hyperparameter Tuning](https://mlsanity.com/paper/1810.05934/) (2018)
- [Multi-Information Source Optimization](https://mlsanity.com/paper/1603.00389/) (2016)
- [ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations](https://mlsanity.com/paper/1908.01425/) (2019)
- [Pre-trained Gaussian Processes for Bayesian Optimization](https://mlsanity.com/paper/2109.08215/) (2021)
- [Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning](https://mlsanity.com/paper/1909.12552/) (2019)
- [Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior](https://mlsanity.com/paper/1811.09558/) (2018)
- [Transfer Learning for Bayesian Optimization: A Survey](https://mlsanity.com/paper/2302.05927/) (2023)
- [Practical Transfer Learning for Bayesian Optimization](https://mlsanity.com/paper/1802.02219/) (2018)
- [Transfer Learning with Gaussian Processes for Bayesian Optimization](https://mlsanity.com/paper/2111.11223/) (2021)
- [Warm Starting Bayesian Optimization](https://mlsanity.com/paper/1608.03585/) (2016)
- [Hyperparameter Learning via Distributional Transfer](https://mlsanity.com/paper/1810.06305/) (2018)
- [Transfer Learning based Search Space Design for Hyperparameter Tuning](https://mlsanity.com/paper/2206.02511/) (2022)
- [Global Optimization with Parametric Function Approximation](https://mlsanity.com/paper/2211.09100/) (2022)

## Built on by (most cited first, 1 of 1)

- [Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization](https://mlsanity.com/paper/2605.04895/) (2026)

## Abstract (arXiv)

We study how to accelerate Bayesian optimization (BO) on a target task by transferring historical knowledge from related source tasks. Existing work on BO with knowledge transfer either lacks theoretical guarantees or achieves the same regret as BO in the non-transfer setting, widetildeO(√T γf), where T is the number of evaluations of the target function and γf denotes its information gain. In this paper, we propose the DeltaBO algorithm, which builds a novel uncertainty-quantification approach on the difference function δ between the source and target functions, which are allowed to belong to different Reproducing Kernel Hilbert Spaces (RKHSs). Under mild assumptions, we prove that the regret of DeltaBO is of order widetildeO(√T (T/N + γδ)), where N denotes the number of evaluations from source tasks and typically N gg T. In many applications, source and target tasks are similar, which implies that γδ can be much smaller than γf. Empirical studies on both real-world hyperparameter-tuning tasks and synthetic functions show that DeltaBO outperforms other baseline methods and also verify our theoretical claims. Our code is available on GitHub.