mlsanityData to 7 Oct 2026

A survey on multi-objective hyperparameter optimization algorithms for Machine Learning

arXiv 2111.13755 ↗First posted 23 Nov 2021cs.LG cs.AI math.OCcited by 24

Not on the map. Why?

Abstract (arXiv)

Hyperparameter optimization (HPO) is a necessary step to ensure the best possible performance of Machine Learning (ML) algorithms. Several methods have been developed to perform HPO; most of these are focused on optimizing one performance measure (usually an error-based measure), and the literature on such single-objective HPO problems is vast. Recently, though, algorithms have appeared that focus on optimizing multiple conflicting objectives simultaneously. This article presents a systematic survey of the literature published between 2014 and 2020 on multi-objective HPO algorithms, distinguishing between metaheuristic-based algorithms, metamodel-based algorithms, and approaches using a mixture of both. We also discuss the quality metrics used to compare multi-objective HPO procedures and present future research directions.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 28 of its 188 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

28 of 188 references.

References · 28

  1. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  3. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
  4. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  5. 2017Population Based Training of Neural Networkscited by 351
  6. 2020On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practicecited by 181
  7. 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 151
  8. 2014ParamILS: An Automatic Algorithm Configuration Frameworkcited by 88
  9. 2020NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Searchcited by 75
  10. 2020Provably Efficient Online Hyperparameter Optimization with Population-Based Banditscited by 61
  11. 2019AtomNAS: Fine-Grained End-to-End Neural Architecture Searchcited by 40
  12. 2019Hyp-RL : Hyperparameter Optimization by Reinforcement Learningcited by 36
16 more
  1. 2017Replication or exploration? Sequential design for stochastic simulation experimentscited by 28
  2. 2016Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraintscited by 27
  3. 2015A Bayesian approach to constrained single- and multi-objective optimizationcited by 23
  4. 2019Evolutionary Neural AutoML for Deep Learningcited by 20
  5. 2018Designing Adaptive Neural Networks for Energy-Constrained Image Classificationcited by 18
  6. 2019Enabling hyperparameter optimization in sequential autoencoders for spiking neural datacited by 18
  7. 2019Multi-objective Bayesian optimisation with preferences over objectivescited by 16
  8. 2017HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networkscited by 11
  9. 2019Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classificationcited by 11
  10. 2019Towards modular and programmable architecture searchcited by 11
  11. 2019Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance targeting Neuromorphic Processorscited by 11
  12. 2016Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimizationcited by 9
  13. 2019PABO: Pseudo Agent-Based Multi-Objective Bayesian Hyperparameter Optimization for Efficient Neural Accelerator Designcited by 7
  14. 2018A Parallel Random Forest Algorithm for Big Data in a Spark Cloud Computing Environmentcited by 6
  15. 2020GPU Accelerated Exhaustive Search for Optimal Ensemble of Black-Box Optimization Algorithmscited by 5
  16. 2018Complexity Theory for Discrete Black-Box Optimization Heuristicscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 4; 2025: 6; 2026: 3.

24 papers.

Sort:

  1. 2023AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Riskscited by 34
  2. 2023LightCTS: A Lightweight Framework for Correlated Time Series Forecastingcited by 18
  3. 2023Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoMLcited by 16
  4. 2023Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learningcited by 8
  5. 2023Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Modelscited by 6
  6. 2024Multi-objective Deep Learning: Taxonomy and Survey of the State of the Artcited by 6
  7. 2022General Cyclical Training of Neural Networkscited by 5
  8. 2023Multi-Objective Population Based Trainingcited by 4
  9. 2025Beyond transparency: computational reliabilism as an externalist epistemology of algorithmscited by 4
  10. 2022Mind the Gap: Measuring Generalization Performance Across Multiple Objectivescited by 3
  11. 2023Dual-stage optimizer for systematic overestimation adjustment applied to multi-objective genetic algorithms for biomarker selectioncited by 2
  12. 2025The Power of the Pareto Front: Balancing Uncertain Rewards for Adaptive Experimentation in scanning probe microscopycited by 2
12 more
  1. 2023HyperTuner: A Cross-Layer Multi-Objective Hyperparameter Auto-Tuning Framework for Data Analytic Servicescited by 1
  2. 2024A Trajectory-Based Bayesian Approach to Multi-Objective Hyperparameter Optimization with Epoch-Aware Trade-Offscited by 1
  3. 2025Reward driven discovery of the optimal microstructure representations with invariant variational autoencoderscited by 1
  4. 2022Policy learning for many outcomes of interest: Combining optimal policy trees with multi-objective Bayesian optimisationcited by 0
  5. 2024Damped Gauss Newton Search for Multi Metric Hyperparameter Optimizationcited by 0
  6. 2024Regularized boosting with an increasing coefficient magnitude stop criterion as meta-learner in hyperparameter optimization stacking ensemblecited by 0
  7. 2025Application of the Brain Drain Optimization Algorithm to the N-Queens Problemcited by 0
  8. 2025Interpreting Graph Inference with Skyline Explanationscited by 0
  9. 2025Development of a Multiprocessing Interface Genetic Algorithm for Optimising a Multilayer Perceptron for Disease Predictioncited by 0
  10. 2026Dynamic Hyperparameter Importance for Efficient Multi-Objective Optimizationcited by 0
  11. 2026Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networkscited by 0
  12. 2026Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Predictioncited by 0