English
Related papers

Related papers: SWAP-NAS: Sample-Wise Activation Patterns for Ultr…

200 papers

Zero-shot proxies, also known as training-free metrics, are widely adopted to reduce the computational overhead in neural network evaluation for scenarios such as Neural Architecture Search (NAS), as they do not require any training.…

Machine Learning · Computer Science 2026-05-11 Yameng Peng , Andy Song , HaythamM. Fayek , Vic Ciesielski , Xiaojun Chang

Recent neural architecture search (NAS) works proposed training-free metrics to rank networks which largely reduced the search cost in NAS. In this paper, we revisit these training-free metrics and find that: (1) the number of parameters…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Taojiannan Yang , Linjie Yang , Xiaojie Jin , Chen Chen

Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce…

Machine Learning · Computer Science 2021-03-22 Mohamed S. Abdelfattah , Abhinav Mehrotra , Łukasz Dudziak , Nicholas D. Lane

Artificial neural networks have been shown to be state-of-the-art machine learning models in a wide variety of applications, including natural language processing and image recognition. However, building a performant neural network is a…

Machine Learning · Computer Science 2025-02-20 Raphael T. Husistein , Markus Reiher , Marco Eckhoff

Training-free network architecture search (NAS) aims to discover high-performing networks with zero-cost proxies, capturing network characteristics related to the final performance. However, network rankings estimated by previous…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Junghyup Lee , Bumsub Ham

In the last decade, zero-cost metrics have gained prominence in neural architecture search (NAS) due to their ability to evaluate architectures without training. These metrics are significantly faster and less computationally expensive than…

Machine Learning · Computer Science 2025-07-08 Ekaterina Gracheva

Training-free Neural Architecture Search (NAS) efficiently identifies high-performing neural networks using zero-cost (ZC) proxies. Unlike multi-shot and one-shot NAS approaches, ZC-NAS is both (i) time-efficient, eliminating the need for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Sofia Casarin , Sergio Escalera , Oswald Lanz

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…

Machine Learning · Computer Science 2021-10-29 Vasco Lopes , Saeid Alirezazadeh , Luís A. Alexandre

Neural architecture search (NAS) is a promising approach for automatically designing neural network architectures. However, the architecture estimation of NAS is computationally expensive and time-consuming because of training multiple…

Machine Learning · Computer Science 2025-08-07 Kun Jing , Luoyu Chen , Jungang Xu , Jianwei Tai , Yiyu Wang , Shuaimin Li

A promising alternative to the computationally expensive Neural Architecture Search (NAS) involves the development of Zero Cost Proxies (ZCPs), which correlate well with trained performance, but can be computed through a single…

Machine Learning · Computer Science 2025-11-20 Richard Goldman , Varun Komperla , Thomas Ploetz , Harish Haresamudram

Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Although many performance predictors correlate well with ground…

Machine Learning · Computer Science 2024-08-14 Gabriela Kadlecová , Jovita Lukasik , Martin Pilát , Petra Vidnerová , Mahmoud Safari , Roman Neruda , Frank Hutter

Neural Architecture Search (NAS) has significantly improved productivity in the design and deployment of neural networks (NN). As NAS typically evaluates multiple models by training them partially or completely, the improved productivity…

Machine Learning · Computer Science 2022-12-22 Yash Akhauri , J. Pablo Munoz , Nilesh Jain , Ravi Iyer

This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of…

Machine Learning · Computer Science 2023-01-02 Wuyang Chen , Xinyu Gong , Junru Wu , Yunchao Wei , Humphrey Shi , Zhicheng Yan , Yi Yang , Zhangyang Wang

Reliable yet efficient evaluation of generalisation performance of a proposed architecture is crucial to the success of neural architecture search (NAS). Traditional approaches face a variety of limitations: training each architecture to…

Machine Learning · Statistics 2021-06-09 Binxin Ru , Clare Lyle , Lisa Schut , Miroslav Fil , Mark van der Wilk , Yarin Gal

One of the primary challenges impeding the progress of Neural Architecture Search (NAS) is its extensive reliance on exorbitant computational resources. NAS benchmarks aim to simulate runs of NAS experiments at zero cost, remediating the…

Machine Learning · Computer Science 2024-06-19 Afzal Ahmad , Linfeng Du , Zhiyao Xie , Wei Zhang

Neural Architecture Search (NAS) is a powerful technique for discovering high-performing CNN architectures, but most existing methods rely on costly training or extensive sampling. Zero-shot NAS offers a training-free alternative by using…

Machine Learning · Computer Science 2025-05-27 Ye Qiao , Jingcheng Li , Haocheng Xu , Sitao Huang

Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method,…

Machine Learning · Computer Science 2025-06-23 Zhenhan Huang , Tejaswini Pedapati , Pin-Yu Chen , Chunheng Jiang , Jianxi Gao

Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Zhuowei Li , Yibo Gao , Zhenzhou Zha , Zhiqiang HU , Qing Xia , Shaoting Zhang , Dimitris N. Metaxas

The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive;…

Machine Learning · Computer Science 2021-06-14 Joseph Mellor , Jack Turner , Amos Storkey , Elliot J. Crowley

Estimating the network performance using zero-cost (ZC) metrics has proven both its efficiency and efficacy in Neural Architecture Search (NAS). However, a notable limitation of most ZC proxies is their inconsistency, as reflected by the…

Neural and Evolutionary Computing · Computer Science 2025-05-23 Quan Minh Phan , Ngoc Hoang Luong
‹ Prev 1 2 3 10 Next ›