mlsanityData to 7 Oct 2026

Multi-Objective Population Based Training

arXiv 2306.01436 ↗First posted 2 Jun 2023cs.LG cs.NEcited by 4

Not on the map. Why?

Abstract (arXiv)

Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. PBT is a single-objective algorithm, but many real-world hyperparameter optimization problems involve two or more conflicting objectives. In this work, we therefore introduce a multi-objective version of PBT, MO-PBT. Our experiments on diverse multi-objective hyperparameter optimization problems (Precision/Recall, Accuracy/Fairness, Accuracy/Adversarial Robustness) show that MO-PBT outperforms random search, single-objective PBT, and the state-of-the-art multi-objective hyperparameter optimization algorithm MO-ASHA.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 36 of its 60 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

36 of 60 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2016Wide Residual Networkscited by 3,057
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  10. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
  11. 2014OpenML: networked science in machine learningcited by 523
  12. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
24 more
  1. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  2. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  3. 2017Population Based Training of Neural Networkscited by 351
  4. 2015Non-stochastic Best Arm Identification and Hyperparameter Optimizationcited by 219
  5. 2018A System for Massively Parallel Hyperparameter Tuningcited by 201
  6. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
  7. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  8. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  9. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  10. 2021Fair Mixup: Fairness via Interpolationcited by 109
  11. 2018A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizationscited by 98
  12. 2020Provably Efficient Online Hyperparameter Optimization with Population-Based Banditscited by 61
  13. 2020Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimizationcited by 60
  14. 2021On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learningcited by 59
  15. 2020Fairness Metrics: A Comparative Analysiscited by 45
  16. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  17. 2022Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overviewcited by 37
  18. 2021A survey on multi-objective hyperparameter optimization algorithms for Machine Learningcited by 24
  19. 2021Multi-objective Asynchronous Successive Halvingcited by 22
  20. 2022Bayesian Generational Population-Based Trainingcited by 20
  21. 2021Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimizationcited by 19
  22. 2021A multi-objective perspective on jointly tuning hardware and hyperparameterscited by 12
  23. 2021Faster Improvement Rate Population Based Trainingcited by 12
  24. 2020Regularized Evolutionary Population-Based Trainingcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2023Scalarization for Multi-Task and Multi-Domain Learning at Scalecited by 19
  2. 2024EmoDM: A Diffusion Model for Evolutionary Multi-objective Optimizationcited by 6
  3. 2025Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisationcited by 0
  4. 2025Iterated Population Based Training with Task-Agnostic Restartscited by 0