# Explaining Hyperparameter Optimization via Partial Dependence Plots

arXiv: https://arxiv.org/abs/2111.04820 · HTML: https://mlsanity.com/paper/2111.04820/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 8 Nov 2021.

## Builds on (most cited first, 11 of 11)

- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models](https://mlsanity.com/paper/1612.08468/) (2016)
- [Tunability: Importance of Hyperparameters of Machine Learning Algorithms](https://mlsanity.com/paper/1802.09596/) (2018)
- [Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL](https://mlsanity.com/paper/2006.13799/) (2020)
- [A Simple and Effective Model-Based Variable Importance Measure](https://mlsanity.com/paper/1805.04755/) (2018)
- [Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach](https://mlsanity.com/paper/2006.04628/) (2020)
- [Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems](https://mlsanity.com/paper/2001.06509/) (2020)
- [Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces](https://mlsanity.com/paper/1409.4011/) (2014)
- [mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions](https://mlsanity.com/paper/1703.03373/) (2017)
- [VINE: Visualizing Statistical Interactions in Black Box Models](https://mlsanity.com/paper/1904.00561/) (2019)
- [Towards Human Centered AutoML](https://mlsanity.com/paper/1911.02391/) (2019)

## Built on by (most cited first, 30 of 35)

- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks](https://mlsanity.com/paper/2306.08107/) (2023)
- [Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena](https://mlsanity.com/paper/2206.05487/) (2022)
- [XAI for All: Can Large Language Models Simplify Explainable AI?](https://mlsanity.com/paper/2401.13110/) (2024)
- [Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML](https://mlsanity.com/paper/2303.08485/) (2023)
- [PED-ANOVA: Efficiently Quantifying Hyperparameter Importance in Arbitrary Subspaces](https://mlsanity.com/paper/2304.10255/) (2023)
- [Position: A Call to Action for a Human-Centered AutoML Paradigm](https://mlsanity.com/paper/2406.03348/) (2024)
- [Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective](https://mlsanity.com/paper/2304.06412/) (2023)
- [Hyperparameter Importance Analysis for Multi-Objective AutoML](https://mlsanity.com/paper/2405.07640/) (2024)
- [Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning](https://mlsanity.com/paper/2309.03581/) (2023)
- [Explainable Bayesian Optimization](https://mlsanity.com/paper/2401.13334/) (2024)
- [Model-agnostic variable importance for predictive uncertainty: an entropy-based approach](https://mlsanity.com/paper/2310.12842/) (2023)
- [iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios](https://mlsanity.com/paper/2306.07775/) (2023)
- [The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research](https://mlsanity.com/paper/2310.07882/) (2023)
- [Efficient and Accurate Explanation Estimation with Distribution Compression](https://mlsanity.com/paper/2406.18334/) (2024)
- [CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC](https://mlsanity.com/paper/2407.05789/) (2024)
- [HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization](https://mlsanity.com/paper/2502.01276/) (2025)
- [Improving Accuracy of Interpretability Measures in Hyperparameter Optimization via Bayesian Algorithm Execution](https://mlsanity.com/paper/2206.05447/) (2022)
- [Communicating Uncertainty in Machine Learning Explanations: A Visualization Analytics Approach for Predictive Process Monitoring](https://mlsanity.com/paper/2304.05736/) (2023)
- [CliMB: An AI-enabled Partner for Clinical Predictive Modeling](https://mlsanity.com/paper/2410.03736/) (2024)
- [Data and AI governance: Promoting equity, ethics, and fairness in large language models](https://mlsanity.com/paper/2508.03970/) (2025)
- [Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization](https://mlsanity.com/paper/2511.02570/) (2025)
- [Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores](https://mlsanity.com/paper/2512.01080/) (2025)
- [DeepCAVE: A Visualization and Analysis Tool for Automated Machine Learning](https://mlsanity.com/paper/2512.01810/) (2025)
- [Practitioner Motives to Use Different Hyperparameter Optimization Methods](https://mlsanity.com/paper/2203.01717/) (2022)
- [Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposal](https://mlsanity.com/paper/2302.03180/) (2023)
- [FastBO: Fast HPO and NAS with Adaptive Fidelity Identification](https://mlsanity.com/paper/2409.00584/) (2024)
- [R+R:Understanding Hyperparameter Effects in DP-SGD](https://mlsanity.com/paper/2411.02051/) (2024)
- [Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectives](https://mlsanity.com/paper/2504.03847/) (2025)
- [Accumulated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models](https://mlsanity.com/paper/2510.08465/) (2025)

## Abstract (arXiv)

Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models. However, there is often a lack of valuable insights into the effects of different hyperparameters on the final model performance. This lack of explainability makes it difficult to trust and understand the automated HPO process and its results. We suggest using interpretable machine learning (IML) to gain insights from the experimental data obtained during HPO with Bayesian optimization (BO). BO tends to focus on promising regions with potential high-performance configurations and thus induces a sampling bias. Hence, many IML techniques, such as the partial dependence plot (PDP), carry the risk of generating biased interpretations. By leveraging the posterior uncertainty of the BO surrogate model, we introduce a variant of the PDP with estimated confidence bands. We propose to partition the hyperparameter space to obtain more confident and reliable PDPs in relevant sub-regions. In an experimental study, we provide quantitative evidence for the increased quality of the PDPs within sub-regions.