Metraipolis › archive › dc_705c18b9ef35
MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search — arXiv:2610.33358
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33358
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:41.862Z
- SHA-256 of the archived text
70b8fc4ab2585cd756d137cdafb7d192a3256b8a8a6f1acbf5b8e74d1de0c583- Stable URL of this page
https://metraipolis.com/documento/dc_705c18b9ef35
How to cite
MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search — arXiv:2610.33358 — arXiv (en), https://arxiv.org/abs/2610.33358 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_705c18b9ef35 (Metraipolis archive dc_705c18b9ef35, sha256 70b8fc4ab2585cd756d137cdafb7d192a3256b8a8a6f1acbf5b8e74d1de0c583)
BibTeX
@misc{dc705c18b9ef35,
title = {MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search — arXiv:2610.33358},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33358},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_705c18b9ef35; sha256 70b8fc4ab2585cd756d137cdafb7d192a3256b8a8a6f1acbf5b8e74d1de0c583},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33358. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hardware-aware neural architecture search (NAS) requires jointly optimizing predictive accuracy and device-specific latency over discrete search spaces. While multi-objective swarm optimizers show promise, continuous formulations such as the Multi-Objective White Shark Optimizer (MOWSO) can suffer from quantization noise when rounded to integer-encoded architecture vectors. To address this limitation, we propose MOSHO (Multi-Objective Shark Hunting Optimization), a native discrete metaheuristic that replaces continuous motion equations with discrete architecture-editing operators. MOSHO integrates adaptive operator scheduling, energy-regulated restarts, and deferred crowding-distance truncation to enhance exploration and search efficiency. On the merged NAS-Bench-201/HW-NAS-Bench benchmark across 18 contexts, MOSHO achieves a median normalized hypervolume of 0.9987 and IGD+ of 0.0064, yielding Pareto fronts competitive with NSGA-II while reducing search runtime by 96.4% (0.64 s vs. 17.72 s). These results demonstrate that tailored discrete search mechanisms can enable swarm optimizers to achieve high-quality multi-objective solution quality with substantially lower search cost in hardware-aware NAS. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.33358 — 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 2026-10-27T07:55:30.822Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).