AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Extensible and Efficient Proxy for Neural Architecture Search

Yuhong Li, Jiajie Li, Cong Hao, Pan Li, Jinjun Xiong, Deming Chen

ICCV 2023 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add untrained barrier layer to few-shot regression proxy (ablation)Eproxy · NAS-Bench-101, 10 iterations, LR 1Spearman rho: 0.08 -> 0.65Improved
add Discrete Proxy Search to Eproxy (ablation)Eproxy · NAS-Bench-101Spearman rho: 0.65 -> 0.69Improved
add Discrete Proxy Search to Eproxy (ablation)Eproxy · NAS-Bench-Trans-Micro averageSpearman rho: 0.29 -> 0.69Improved
add Discrete Proxy Search to Eproxy (ablation)Eproxy · NAS-Bench-MR averageSpearman rho: 0.27 -> 0.51Improved
add Discrete Proxy Search to Eproxy (ablation)Eproxy · NDS ImageNet average (transferred)Spearman rho: 0.55 -> 0.73Improved
Eproxy without DPS versus NASWOT on NDS CIFAR-10Eproxy · NDS CIFAR-10 averageSpearman rho: 0.43 -> 0.41No clear effect
Eproxy without DPS on NAS-Bench-Trans-Micro versus other proxies in ranking correlationEproxy · NAS-Bench-Trans-Micro averageSpearman rho: 0.47 -> 0.29Hurt
use Eproxy+DPS instead of early stopping on target tasksEproxy+DPS · NAS-Bench-Trans-Micro averageSpearman rho: 0.43 -> 0.69Improved
use Eproxy+DPS as fitness for regularized evolution on NAS-Bench-201Eproxy+DPS · NAS-Bench-201 CIFAR-10queries to optimum: 563.2 -> 58.0 + 20Improved
NAS with Eproxy+DPS on DARTS-ImageNetEproxy+DPS · DARTS ImageNet top-1 errortest error: 25.7 -> 24.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy