# High-Dimensional Bayesian Optimization with Multi-Task Learning for RocksDB

arXiv: https://arxiv.org/abs/2103.16267 · HTML: https://mlsanity.com/paper/2103.16267/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Gaussian Processes for Big Data](https://mlsanity.com/paper/1309.6835/) (2013)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [pymoo: Multi-objective Optimization in Python](https://mlsanity.com/paper/2002.04504/) (2020)
- [Bayesian Optimization in a Billion Dimensions via Random Embeddings](https://mlsanity.com/paper/1301.1942/) (2013)
- [Multi-fidelity Bayesian Optimisation with Continuous Approximations](https://mlsanity.com/paper/1703.06240/) (2017)
- [Device Placement Optimization with Reinforcement Learning](https://mlsanity.com/paper/1706.04972/) (2017)
- [BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization](https://mlsanity.com/paper/1910.06403/) (2019)
- [The Case for Automatic Database Administration using Deep Reinforcement Learning](https://mlsanity.com/paper/1801.05643/) (2018)
- [LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations](https://mlsanity.com/paper/1808.07903/) (2018)
- [Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper](https://mlsanity.com/paper/1702.00505/) (2017)
- [Towards a General Framework for ML-based Self-tuning Databases](https://mlsanity.com/paper/2011.07921/) (2020)

## Built on by (most cited first, 4 of 4)

- [Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning](https://mlsanity.com/paper/2402.03183/) (2024)
- [One Model to Rule them All: Towards Zero-Shot Learning for Databases](https://mlsanity.com/paper/2105.00642/) (2021)
- [Deep Configuration Performance Learning: A Systematic Survey and Taxonomy](https://mlsanity.com/paper/2403.03322/) (2024)
- [Learning to Score: Tuning Cluster Schedulers through Reinforcement Learning](https://mlsanity.com/paper/2603.10545/) (2026)

## Abstract (arXiv)

RocksDB is a general-purpose embedded key-value store used in multiple different settings. Its versatility comes at the cost of complex tuning configurations. This paper investigates maximizing the throughput of RocksDB IO operations by auto-tuning ten parameters of varying ranges. Off-the-shelf optimizers struggle with high-dimensional problem spaces and require a large number of training samples. We propose two techniques to tackle this problem: multi-task modeling and dimensionality reduction through a manual grouping of parameters. By incorporating adjacent optimization in the model, the model converged faster and found complicated settings that other tuners could not find. This approach had an additional computational complexity overhead, which we mitigated by manually assigning parameters to each sub-goal through our knowledge of RocksDB. The model is then incorporated in a standard Bayesian Optimization loop to find parameters that maximize RocksDB's IO throughput. Our method achieved x1.3 improvement when benchmarked against a simulation of Facebook's social graph traffic, and converged in ten optimization steps compared to other state-of-the-art methods that required fifty steps.