Papers › Multi-objective Asynchronous Successive Halving

Multi-objective Asynchronous Successive Halving

23 Jun 2021arXiv:2106.12639archive 2025-07-28

Robin Schmucker, Michele Donini, Muhammad Bilal Zafar, David Salinas, Cédric Archambeau

Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-world applications, accuracy is only one of the multiple -- often conflicting -- performance criteria, necessitating the adoption of a multi-objective (MO) perspective. While the literature on MO optimization is rich, few prior studies have focused on HPO. In this paper, we propose algorithms that extend asynchronous successive halving (ASHA) to the MO setting. Considering multiple evaluation metrics, we assess the performance of these methods on three real world tasks: (i) Neural architecture search, (ii) algorithmic fairness and (iii) language model optimization. Our empirical analysis shows that MO ASHA enables to perform MO HPO at scale. Further, we observe that that taking the entire Pareto front into account for candidate selection consistently outperforms multi-fidelity HPO based on MO scalarization in terms of wall-clock time. Our algorithms (to be open-sourced) establish new baselines for future research in the area.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mbilalzafar/fair-classification officialmentioned in paper report
awslabs/autogluon mxnetApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

FairnessHyperparameter OptimizationLanguage ModelingLanguage ModellingModel OptimizationNeural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

HPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections