English
Related papers

Related papers: Stronger NAS with Weaker Predictors

200 papers

Neural architecture search (NAS) has achieved breakthrough success in a great number of applications in the past few years. It could be time to take a step back and analyze the good and bad aspects in the field of NAS. A variety of…

Computer Vision and Pattern Recognition · Computer Science 2020-01-16 Xuanyi Dong , Yi Yang

Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by…

Machine Learning · Computer Science 2022-06-07 Colin White , Willie Neiswanger , Sam Nolen , Yash Savani

Many studies estimate energy consumption using proxy metrics like memory usage, FLOPs, and inference latency, with the assumption that reducing these metrics will also lower energy consumption in neural networks. This paper, however, takes…

Machine Learning · Computer Science 2025-04-14 Hoang-Loc La , Phuong Hoai Ha

Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this…

Machine Learning · Computer Science 2021-10-13 Jingtao Rong , Xinyi Yu , Mingyang Zhang , Linlin Ou

Neural Architecture Search (NAS) has become a popular method for discovering effective model architectures, especially for target hardware. As such, NAS methods that find optimal architectures under constraints are essential. In our paper,…

Machine Learning · Computer Science 2023-04-25 Yicheng Fan , Dana Alon , Jingyue Shen , Daiyi Peng , Keshav Kumar , Yun Long , Xin Wang , Fotis Iliopoulos , Da-Cheng Juan , Erik Vee

Neural Architecture Search (NAS) defines the design of Neural Networks as a search problem. Unfortunately, NAS is computationally intensive because of various possibilities depending on the number of elements in the design and the possible…

Machine Learning · Computer Science 2023-11-20 Brian Moser , Federico Raue , Jörn Hees , Andreas Dengel

Data-driven, automatic design space exploration of neural accelerator architecture is desirable for specialization and productivity. Previous frameworks focus on sizing the numerical architectural hyper-parameters while neglect searching…

Machine Learning · Computer Science 2021-05-28 Yujun Lin , Mengtian Yang , Song Han

The search space of neural architecture search (NAS) for convolutional neural network (CNN) is huge. To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only. Such…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Chunnan Wang , Hongzhi Wang , Guosheng Feng , Fei Geng

We achieve very efficient deep learning model deployment that designs neural network architectures to fit different hardware constraints. Given a constraint, most neural architecture search (NAS) methods either sample a set of sub-networks…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Sian-Yao Huang , Wei-Ta Chu

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

Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate connections. Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Yibo Yang , Hongyang Li , Shan You , Fei Wang , Chen Qian , Zhouchen Lin

Evaluation is a critical but costly procedure in neural architecture search (NAS). Performance predictors have been widely adopted to reduce evaluation costs by directly estimating architecture performance. The effectiveness of predictors…

Machine Learning · Computer Science 2025-06-09 Han Ji , Yuqi Feng , Jiahao Fan , Yanan Sun

In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based…

Machine Learning · Computer Science 2019-07-11 Yanqi Zhou , Peng Wang , Sercan Arik , Haonan Yu , Syed Zawad , Feng Yan , Greg Diamos

Neural Architecture Search (NAS) is a research field concerned with utilizing optimization algorithms to design optimal neural network architectures. There are many approaches concerning the architectural search spaces, optimization…

Machine Learning · Computer Science 2020-05-25 George Kyriakides , Konstantinos Margaritis

Despite remarkable progress achieved, most neural architecture search (NAS) methods focus on searching for one single accurate and robust architecture. To further build models with better generalization capability and performance, model…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Minghao Chen , Houwen Peng , Jianlong Fu , Haibin Ling

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however,…

Machine Learning · Computer Science 2021-02-24 Niv Nayman , Yonathan Aflalo , Asaf Noy , Lihi Zelnik-Manor

The emergence of neural architecture search (NAS) has greatly advanced the research on network design. Recent proposals such as gradient-based methods or one-shot approaches significantly boost the efficiency of NAS. In this paper, we…

Machine Learning · Computer Science 2019-12-09 Yizhou Zhou , Xiaoyan Sun , Chong Luo , Zheng-Jun Zha , Wenjun Zeng

Neural Architecture Search (NAS) is a powerful automatic alternative to manual design of a neural network. In the zero-shot version, a fast ranking function is used to compare architectures without training them. The outputs of the ranking…

Machine Learning · Computer Science 2025-02-28 Pavel Rumiantsev , Mark Coates

The significant computational cost of multiplications hinders the deployment of deep neural networks (DNNs) on edge devices. While multiplication-free models offer enhanced hardware efficiency, they typically sacrifice accuracy. As a…

Machine Learning · Computer Science 2024-09-10 Yang Xu , Huihong Shi , Zhongfeng Wang

In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS). The task sounds counter-intuitive for most existing NAS algorithms since random label provides few information…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Xuanyang Zhang , Pengfei Hou , Xiangyu Zhang , Jian Sun