PulseAugur
EN
LIVE 18:37:16

New LESS method slashes neural architecture search time to minutes

By PulseAugur Editorial · [2 sources] ·

Researchers have developed LESS (Lightweight Evolutionary Supernet Search), a novel method for neural architecture search that significantly reduces computation time. By combining a brief warm-up with a discrete search under a CMA-ES distribution, LESS achieves competitive accuracy on benchmarks like CIFAR-10 in minutes, a fraction of the time required by previous methods. The approach demonstrates effectiveness across different datasets and search spaces, including the larger DARTS space, highlighting its efficiency and broad applicability. AI

IMPACT Enables faster and more efficient exploration of AI model architectures, potentially accelerating research and development cycles.

RANK_REASON The cluster contains an academic paper detailing a new method for neural architecture search.

Read on arXiv cs.NE (Neural & Evolutionary) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New LESS method slashes neural architecture search time to minutes

How we ranked this

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster contains an academic paper detailing a new method for neural architecture search.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Aviral Gandhi, Jinglue Xu, Jialong Li, Hitoshi Iba ·

    LESS: Lightweight Evolutionary Supernet Search in Minutes

    arXiv:2610.01468v1 Announce Type: cross Abstract: Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducing evaluation cost often weakens the fidelity of candidate comparisons. Training-free methods reduce evaluation cost by replacing l…

  2. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Hitoshi Iba ·

    LESS: Lightweight Evolutionary Supernet Search in Minutes

    Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducing evaluation cost often weakens the fidelity of candidate comparisons. Training-free methods reduce evaluation cost by replacing learned task feedback with proxy signals measured a…

RELATED ENTITIES

RELATED TOPICS