Metraipolis › archive › dc_fb27d403fa53

Early-Stopping Thresholds for ES-HyperNEAT: A Data-Driven Approach from Fitness Dynamics — arXiv:2609.13533

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13533
License (as archived): CC0-1.0
Archived: 2026-10-16T00:14:57.459Z
SHA-256 of the archived text: f75e645f71133ac7bf5dd7801f6f5ae3b7c0e6fadfabee8e37b36aee75543ae5
Stable URL of this page: https://metraipolis.com/documento/dc_fb27d403fa53

How to cite

Early-Stopping Thresholds for ES-HyperNEAT: A Data-Driven Approach from Fitness Dynamics — arXiv:2609.13533 — arXiv (en), https://arxiv.org/abs/2609.13533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb27d403fa53 (Metraipolis archive dc_fb27d403fa53, sha256 f75e645f71133ac7bf5dd7801f6f5ae3b7c0e6fadfabee8e37b36aee75543ae5)

BibTeX

@misc{dcfb27d403fa53,
  title = {Early-Stopping Thresholds for ES-HyperNEAT: A Data-Driven Approach from Fitness Dynamics — arXiv:2609.13533},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13533},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb27d403fa53; sha256 f75e645f71133ac7bf5dd7801f6f5ae3b7c0e6fadfabee8e37b36aee75543ae5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most hyperparameter configurations for Evolvable-Substrate HyperNEAT (ES-HyperNEAT) produce networks that stagnate at random-guessing performance, wasting computational resources. We frame early stopping as binary classification on early fitness trajectories: for each trial, we compute the cumulative median of best-per-generation fitness and test it against a threshold derived by maximizing the F1 score on an initial 90-trial dataset. The resulting rule (generation G* = 3, threshold T* = 0.140) achieves F1 = 0.872 on 180 independent validation trials, retaining over 90% of successful trials while cutting computational cost by 41.6%. Compared to Hyperband, our domain-specific rule is 64% more efficient with higher mean fitness, though Hyperband occasionally discovers higher peak solutions. On a converged search population the rule becomes too aggressive (recall 31.1%), motivating adaptive thresholds. The specific thresholds are ES-HyperNEAT-specific, but the methodology, deriving stopping criteria from fitness dynamics classification, is applicable to other evolutionary algorithms with stagnation-prone hyperparameter spaces.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13533 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.848Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).