AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Multi-Objective Population Based Training

Arkadiy Dushatskiy, Alexander Chebykin, Tanja Alderliesten, Peter Bosman

ICML 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Multi-objective optimization · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use domination-based multi-objective ranking rather than scalarizationPBT for multi-objective hyperparameter optimization · Diverse precision/recall, accuracy/fairness, and accuracy/robustness taskshypervolumeImproved
Use MO-PBT rather than the strongest listed baselineMO-HPO · Precision/Recall, Adulthypervolume: 69.61 ± 0.27 -> 70.59 ± 0.13Improved
Use MO-PBT rather than the strongest listed baselineMO-HPO · Accuracy/Robustness, CIFAR-10hypervolume: 34.74 ± 0.48 -> 35.40 ± 0.09Improved
Optimize only fairness rather than jointly optimizing the objectivesSingle-objective PBT · Accuracy/Fairness taskshypervolumeHurt
Use random scalarization instead of domination-based rankingPBT for multi-objective hyperparameter optimization · Diverse multi-objective taskshypervolumeHurt
Use BO-MO-ASHA instead of MO-ASHAMO-ASHA · Considered multi-objective taskshypervolumeNo clear effect
Use local mutation rather than random mutation (ablation)MO-PBT explore operator · MO-PBT ablation taskshypervolumeImproved
Set truncation selection τ to 25 rather than 10 or 50 (ablation)MO-PBT exploit operator · MO-PBT ablation taskshypervolumeImproved
Use greedy scattered subset selection rather than crowding distance (ablation)MO-PBT ranking · MO-PBT ablation taskshypervolumeImproved
Require accuracy to exceed that of trivial classifiers (ablation)MO-PBT · CelebA Accuracy/DSP and Accuracy/DSP/DEOhypervolumeNo clear effect
Increase population size from 16 to 32 to 64 (ablation)MO-PBT · Scalability experimentshypervolumeImproved
Expand the image-task search space from 5 variables to 31 variables (ablation)MO-PBT · Accuracy/Robustness image taskshypervolumeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy