AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Multi-Objective Neural Architecture Search by Learning Search Space Partitions

Yiyang Zhao, Linnan Wang, Tian Guo

JMLR 2024 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 1 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 LaMOO space partitioning to qEHVIqEHVI · NasBench201log hypervolume difference: 225% sample efficiencyImproved
add LaMOO space partitioning to CMA-ESCMA-ES · NasBench201sample efficiency: 500%Improved
add LaMOO to qEHVIqEHVI · NasBench301hypervolume: 200% search performance improvementImproved
add LaMOO to CMA-ESCMA-ES · NasBench301sample efficiency: more than 250%Improved
add LaMOO to CMA-ESCMA-ES · HW-NAS-Bench (4 objectives)log hypervolume differenceImproved
use few-shot instead of one-shot evaluation (ablation)LaMOO · NasBench201log hypervolume differenceImproved
use vanilla training evaluation instead of few-shot (ablation)LaMOO · NasBench201log hypervolume differenceImproved
use few-shot instead of one-shot LaMOONet (ablation)LaMOONet · CIFAR-10test error (%): 2.85 -> 2.78Improved
use few-shot instead of one-shot LaMOONet (ablation)LaMOONet · CIFAR-10GPU days: 1.18 -> 2.06Hurt
use LaMOO instead of vanilla NAS baselines (LaMOONet-P1)NAS · CIFAR-10#parameters: 1.62M compared to at least 2.8MImproved
use LaMOO instead of AmoebaNet searchNAS · CIFAR-10GPU days: 3150 -> 100Improved
use LaMOO one-shot instead of standard evaluation (ablation)LaMOONet · CIFAR-10test error (%): 2.23 -> 2.85Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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