Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

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

First seen · 9/11/2026, 01:49 AMLatest activity · 9/11/2026, 01:49 AM

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.

Event heat · last 24 hours

There are 8 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 14:00; latest heat is 0.

There are 8 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 14:00; latest heat is 0.10.509/12, 14:00, event heat 09/12, 17:00, event heat 09/12, 20:00, event heat 09/12, 23:00, event heat 09/13, 02:00, event heat 09/13, 05:00, event heat 09/13, 08:00, event heat 09/13, 11:00, event heat 024 hours agoNow
  1. 9/12, 14:00, event heat 0
  2. 9/12, 17:00, event heat 0
  3. 9/12, 20:00, event heat 0
  4. 9/12, 23:00, event heat 0
  5. 9/13, 02:00, event heat 0
  6. 9/13, 05:00, event heat 0
  7. 9/13, 08:00, event heat 0
  8. 9/13, 11:00, event heat 0

Reporting Timeline

  1. AggregatorarXiv9/11, 01:49 AMnot independentRepresentative
    CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search