AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving

Ruochen Wang, Xiangning Chen, Minhao Cheng, Xiaocheng Tang, Cho-Jui Hsieh

ICCV 2021 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 8 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
use NOSH with ranking instead of arch2vec-BO with early stopping at budget 2,969 (ablation)arch2vec-BO · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 90.35 -> 91.56Improved
use NOSH with ranking instead of arch2vec-BO with early stopping at budget 2,969 (ablation)arch2vec-BO · NAS-Bench-201 CIFAR-100 valvalidation accuracy (%): 71.88 -> 73.44Improved
use NOSH with ranking instead of arch2vec-BO with early stopping at budget 2,969 (ablation)arch2vec-BO · NAS-Bench-201 ImageNet16-120 valvalidation accuracy (%): 45.10 -> 46.43Improved
use training-free prior scores alone instead of searching (ablation)mag prior score · NAS-Bench-201 CIFAR-10 testtest accuracy (%): 94.26 -> 93.35Hurt
shorten schedule E from (10,50,100,200) to (5,10,25,200) (ablation)RANK-NOSH · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 91.60 -> 91.57No clear effect
shorten schedule E from (10,50,100,200) to (5,25,50,200) (ablation)RANK-NOSH · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 91.60 -> 91.59No clear effect
drop the 100-epoch level, E=(10,50,200) (ablation)RANK-NOSH · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 91.60 -> 91.60No clear effect
lower move ratio r from 0.5 to 0.3 (ablation)RANK-NOSH · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 91.60 -> 91.40Hurt
raise move ratio r from 0.5 to 0.7 (ablation)RANK-NOSH · NAS-Bench-201 CIFAR-10 valvalidation accuracy (%): 91.60 -> 91.58No clear effect
use RANK-NOSH instead of arch2vec-BO at lower budgetarch2vec-BO · NAS-Bench-201 CIFAR-100 testtest accuracy (%): 73.41 -> 73.51Improved
use RANK-NOSH instead of arch2vec-BO on DARTS spacearch2vec-BO · DARTS space CIFAR-10 avgtest error (%): 2.56 -> 2.53Improved
use RANK-NOSH instead of arch2vec-BO on NAS-Bench-101arch2vec-BO · NAS-Bench-101test accuracy (%): 94.05 -> 93.97No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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