AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization

Yaoming Wang, Yuchen Liu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

ICCV 2021 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 12 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 the architectural neural network (replace vanilla 14x8 parameters) (ablation)VIM-NAS · CIFAR-10 (DARTS space)top-1 test error (%): 2.65 -> 2.45Improved
use a medium architectural network instead of a single ConvReLUBN module (ablation)VIM-NAS · CIFAR-10 (DARTS space)top-1 test error (%): 2.51 -> 2.45Improved
use the default architectural network instead of five modules (ablation)VIM-NAS · CIFAR-10 (DARTS space)top-1 test error (%): 2.58 -> 2.45Improved
use probabilistic posterior instead of the variational-dropout reformulation (ablation)VIM-NAS · CIFAR-10 (DARTS space)top-1 test error (%): 2.58 -> 2.45Improved
use probabilistic distribution instead of point estimation (ablation)VIM-NAS · DARTS spacetop-1 test error (%)Improved
VIM-NAS instead of DARTS-V2DARTS · CIFAR-10top-1 test error (%): 2.76 -> 2.45Improved
VIM-NAS instead of DARTS-V2DARTS · CIFAR-100top-1 test error (%): 17.54 -> 15.80Improved
VIM-NAS instead of DARTS-V1 (search cost, GPU-days)DARTS · CIFAR-10search cost (GPU-days): 0.4 -> 0.007Improved
VIM-NAS instead of DARTS-DARTS- · NAS-Bench-201 CIFAR-100 testaccuracy (%): 71.53 -> 73.07Improved
VIM-NAS instead of DARTS-DARTS- · NAS-Bench-201 ImageNet-16-120 testaccuracy (%): 45.12 -> 46.27Improved
search directly on ImageNet instead of transferring from CIFAR-10VIM-NAS · ImageNettop-1 test error (%): 24.0 -> 23.8Improved
VIM-NAS instead of PC-DARTSPC-DARTS · ImageNettop-1 test error (%): 25.1 -> 24.0Improved

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