paper-with-me

홈 › Papers

EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search

2021-02-16 · Vasco Lopes, Saeid Alirezazadeh, Luís A. Alexandre

Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.

📄 PDF Abstract BibTeX arXiv:2102.08099

Code (2)

VascoLopes/EPE-NAS 공식 구현 pytorch
VascoLopes/EPENAS 공식 구현 pytorch

Tasks

GPUNeural Architecture Search

Similar Papers 제목 키워드 기반

MONAS: Efficient Zero-Shot Neural Architecture Search for MCUs

2024-08-26 · Ye Qiao, Haocheng Xu, Yifan Zhang, Sitao Huang

Neural Architecture Search (NAS) has proven effective in discovering new Convolutional Neural Network (CNN) architectures, particularly for scenarios with well-defined accuracy optimization goals. However, previous appro…

Edge-computingNeural Architecture Search

PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search

2021-01-11 · Ariel Keller Rorabaugh, Silvina Caíno-Lores, Michael R. Wyatt II, Travis Johnston 외

Neural network (NN) models are increasingly used in scientific simulations, AI, and other high performance computing (HPC) fields to extract knowledge from datasets. Each dataset requires tailored NN model architecture, …

Neural Architecture Search

Efficient Multi-Objective Neural Architecture Search via Pareto Dominance-based Novelty Search

2024-07-30 · An Vo, Ngoc Hoang Luong

Neural Architecture Search (NAS) aims to automate the discovery of high-performing deep neural network architectures. Traditional objective-based NAS approaches typically optimize a certain performance metric (e.g., pred…

DiversityNeural Architecture Search

ReNAS: Relativistic Evaluation of Neural Architecture Search

2021-06-19 · CVPR 2021 1 · Yixing Xu, Yunhe Wang, Kai Han, Yehui Tang 외

An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and eval…

Neural Architecture Search

ReNAS:Relativistic Evaluation of Neural Architecture Search

2019-09-30 · Yixing Xu, Yunhe Wang, Kai Han, Yehui Tang 외

An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and evaluate…

Neural Architecture Search