Algorithm Configuration

Optimization
Author

Ziang Liu

Published

October 10, 2025

Let \(\mathcal{I}\) be the set of problem instances, \(\mathcal{D}\) be the probability distribution over \(\mathcal{I}\). Let \(p_1, p_2, \ldots, p_k\) be the parameters of an algorithm. The domain of each parameter \(p_i\) is denoted as \(\Theta_i\), and the parameter space is defined as \(\Theta = \Theta_1 \times \Theta_2 \times \ldots \times \Theta_k\). Note that the the domain of each parameter can be continuous, discrete, or categorical. The parameter configuration of the algorithm is denoted as \(\theta = (p_1, p_2, \ldots, p_k) \in \Theta\).

The objective of algorithm configuration is to find the optimal parameter configuration \(\theta^* \in \Theta\) that minimizes the expected cost of the algorithm over the distribution of problem instances:

\[ \theta^* \in \arg\min_{\theta \in \Theta} \mathbb{E}_{i \sim \mathcal{D}}[c(\theta, i)] \]

where \(c(\theta, i)\) is the cost of the algorithm parameter configuration \(\theta\) on problem instance \(i\).

Normally, the distribution \(\mathcal{D}\) is unknown. Thus, arithmetic mean is often used as an estimator of the expected cost. The problem is then formulated as follows:

\[ \theta^* \in \arg\min_{\theta \in \Theta} \frac{1}{|\mathcal{I}|} \sum_{i \in \mathcal{I}} c(\theta, i) \]

AutoML

Hyperparameter Optimization

Hyperparameter optimization (HPO) is a special case of algorithm configuration.

Dynamic Algorithm Configuration

References

Akiba, Takuya, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. “Optuna: A Next-Generation Hyperparameter Optimization Framework.” Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (New York, NY, USA), 2623–31. https://doi.org/10.1145/3292500.3330701.
Jaderberg, Max, Valentin Dalibard, Simon Osindero, et al. 2017. “Population Based Training of Neural Networks.” arXiv [Cs.LG], ahead of print. https://doi.org/10.48550/arXiv.1711.09846.
Lindauer, Marius, Katharina Eggensperger, Matthias Feurer, et al. 2021. SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization.” arXiv [Cs.LG], ahead of print. https://doi.org/10.48550/arXiv.2109.09831.