AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

$\beta $-DARTS++: Bi-Level Regularization for Proxy-Robust Differentiable Architecture Search

Peng Ye, Tong He, Baopu Li, Tao Chen, Lei Bai, Wanli Ouyang

TPAMI 2025 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 9 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 Beta-Decay regularization to SDARTS-RS (ablation)SDARTS-RS · NAS-Bench-201 ImageNet16-120 testaccuracy (%): 26.29 -> 46.34Improved
add Beta-Decay regularization to RDARTS-L2 (ablation)RDARTS-L2 · NAS-Bench-201 ImageNet16-120 testaccuracy (%): 18.41 -> 46.34Improved
add Beta-Decay regularization to SNAS (ablation)SNAS · NAS-Bench-201 ImageNet16-120 testaccuracy (%): 26.10 -> 46.34Improved
add flooding (beta-DARTS to beta-DARTS++), 1% proxy data (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 91.11 -> 93.20Improved
add flooding (beta-DARTS to beta-DARTS++), 10% proxy data (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 89.89 -> 93.34Improved
add flooding (beta-DARTS to beta-DARTS++), 2% proxy data (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 90.44 -> 93.39Improved
add flooding (beta-DARTS to beta-DARTS++), 1% proxy data (ablation)beta-DARTS · NAS-Bench-201 ImageNet16-120 testaccuracy (%): 40.80 -> 45.47Improved
add flooding (beta-DARTS to beta-DARTS++), 2 proxy channels (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 93.56 -> 93.96Improved
add flooding (beta-DARTS to beta-DARTS++), 1 proxy channel (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 93.76 -> 93.68No clear effect
add weight flooding to DARTS, 8 proxy channels (ablation)DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 54.30 -> 88.28Improved
add weight flooding to DARTS, 1% proxy data (ablation)DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 54.30 -> 54.30No clear effect
search on CIFAR-100 instead of CIFAR-10 (ablation)beta-DARTS · NAS-Bench-201 CIFAR-10 testaccuracy (%): 94.36 -> 93.99Hurt

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