PertNAS: Architectural Perturbations for Memory-Efficient Neural Architecture Search

Differentiable Neural Architecture Search (NAS) relies on aggressive weight-sharing to reduce its search cost. This leads to GPU-memory bottlenecks that hamper the algorithm's scalability. To resolve these bottlenecks, we propose a perturbations-based evolutionary approach that significantly re...

Celý popis

Podrobná bibliografia

Vydané v:	2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autori:	Ahmad, Afzal, Xie, Zhiyao, Zhang, Wei
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 09.07.2023
Predmet:	Costs Design automation Memory architecture Memory management Microprocessors Perturbation methods Scalability
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!