Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-09-10 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.LG · 机器学习 · first seen 2026-09-11

Abstract

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. Co

Read on arXiv →

#72 most recent of 215 cs.LG papers we have recorded · ↑ newer: 3D Point Splatting for mmWave Radar Novel View Synthesis · ↓ older: Evaluating Time-Series Foundation Models and Multimodal Dietary Contex
Cite this page: CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search: the #72 most recent of 215 cs.LG papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/cora-nas-coarse-ranking-and-anchor-residual-refinement-for-neural-architecture-s.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions