Metraipolis › archive › dc_996fb22a1771

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search — arXiv:2609.12418

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12418
License (as archived)
CC0-1.0
Archived
2026-10-16T03:15:41.853Z
SHA-256 of the archived text
563c153ea5f083b1ad581262e8bd8736161d57f6b2f893068adc7b845294dd4c
Stable URL of this page
https://metraipolis.com/documento/dc_996fb22a1771

How to cite

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search — arXiv:2609.12418 — arXiv (en), https://arxiv.org/abs/2609.12418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_996fb22a1771 (Metraipolis archive dc_996fb22a1771, sha256 563c153ea5f083b1ad581262e8bd8736161d57f6b2f893068adc7b845294dd4c)
BibTeX
@misc{dc996fb22a1771,
  title = {RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search — arXiv:2609.12418},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_996fb22a1771; sha256 563c153ea5f083b1ad581262e8bd8736161d57f6b2f893068adc7b845294dd4c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural architecture search (NAS) evaluates candidate networks, but fully training enough architectures to rank an entire space is expensive. Zero-cost proxies score architectures at initialization, yet their ranking quality varies across search spaces. Learned predictors reduce evaluation cost but typically require fully trained labels or partial-training features for individual candidates. We introduce $\textbf{RiPPLE}$, $\underline{\textbf{R}}$anking v$\underline{\textbf{i}}$a $\underline{\textbf{P}}$refix-$\underline{\textbf{P}}$ropagated $\underline{\textbf{L}}$abel $\underline{\textbf{E}}$xtrapolation, which treats partial training as a source of labels for a small coverage set of anchors. RiPPLE trains these anchors to an early prefix, extrapolates their learning curves to surrogate labels, and propagates the labels over label-free architecture features. The early-training signal remains a label on the anchors rather than a per-candidate feature. Feature, readout, and encoding rules are selected without held-out accuracy and reused across search spaces. We evaluate the method on twelve benchmark cells from four search-space families and on the larger DARTS space. The results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation. RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12418 — 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 2026-10-16T03:05:44.042Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).