SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

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}}

Read original source ↗ Open in workspace

recordType

paper

region

Global