SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity and structure-at-initialization proxies through an equal-weight log-rank consensus and a target-free consensus gate. CoRA-Refine samples anchors across this prior, extrapolates their early validation curves, and propagates a learned residual correction with an ExtraTrees model. The refinement uses approximately 1% of

Read original source ↗ Open in workspace

recordType

paper

region

Global