Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
arXiv·Yifan Yang·Sep 10, 2026, 5:49 PM

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

Papers74

While zero-cost proxies evaluate neural architectures with minimal overhead, their ranking reliability frequently degrades across different search spaces. CoRA-NAS counters this instability through a two-stage approach: it establishes a static ranking prior by aggregating initialization proxies, then samples anchor models and extrapolates their early validation curves to propagate residual corrections via an ExtraTrees model. Requiring roughly 1% of full training compute without relying on ground-truth training labels, CoRA-NAS achieves mean Spearman correlations between 0.715 and 0.946 across four standard NAS benchmarks, selecting top architectures within 0.05% of the benchmark ceiling.

Why it's worth reading

CoRA-NAS tackles the cross-space inconsistency of zero-cost proxies by anchoring early learning curves at just 1% compute overhead, offering a robust and practical middle ground for architecture search.

Tags

AutoMLNASZero-Cost ProxiesNeural Architecture SearchModel Efficiency

Score breakdown

  • Novelty75
  • Impact72
  • Practicality78
  • Credibility75
  • Timeliness70