Filters








8 Hits in 4.3 sec

HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin
2021 International Conference on Learning Representations  
HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous attention by automating the design of deep neural networks deployed in more resource-constrained daily life devices.  ...  To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e.g., energy cost and latency) of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six  ...  the great necessity of HW-NAS benchmarks like our proposed HW-NAS-Bench.  ... 
dblp:conf/iclr/LiYFZZYY0HL21 fatcat:spv6yciqpvh4lnyexe7aw4yse4

EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search [article]

Qian Jiang, Xiaofan Zhang, Deming Chen, Minh N. Do, Raymond A. Yeh
2021 arXiv   pre-print
In hardware-aware Differentiable Neural Architecture Search (DNAS), it is challenging to compute gradients of hardware metrics to perform architecture search.  ...  In this work, we propose End-to-end Hardware-aware DNAS (EH-DNAS), a seamless integration of end-to-end hardware benchmarking, and fully automated DNAS to deliver hardware-efficient deep neural networks  ...  Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Hw-nas-bench: Hardware-aware neural architecture search Jia, and  ... 
arXiv:2111.12299v1 fatcat:hrtt7wr6ifep5nrhlruyeqajre

HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning [article]

Hayeon Lee, Sewoong Lee, Song Chong, Sung Ju Hwang
2021 arXiv   pre-print
For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency  ...  Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator.  ...  in HW-NAS-Bench dataset [43] .  ... 
arXiv:2106.08630v3 fatcat:oxpeke4twbdvro3tlbrku4nuai

Learning Where To Look – Generative NAS is Surprisingly Efficient [article]

Jovita Lukasik, Steffen Jung, Margret Keuper
2022 arXiv   pre-print
The efficient, automated search for well-performing neural architectures (NAS) has drawn increasing attention in the recent past.  ...  To this aim, surrogate models embed architectures in a latent space and predict their performance, while generative models for neural architectures enable optimization-based search within the latent space  ...  A.5 Hardware-Aware-NAS-Bench The recently introduced HW-NAS-Bench [30] is the first public dataset for hardware NAS.  ... 
arXiv:2203.08734v2 fatcat:mrjt27bauvhh5gdlsll2wzohee

NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters [article]

Yoichi Hirose, Nozomu Yoshinari, Shinichi Shirakawa
2021 arXiv   pre-print
The benchmark datasets for neural architecture search (NAS) have been developed to alleviate the computationally expensive evaluation process and ensure a fair comparison.  ...  We collect the performance data of 4K cell-based convolutional neural network architectures trained on the CIFAR-10 dataset with different learning rate and batch size settings, resulting in the data of  ...  (Klyuchnikov et al., 2020) for natural language processing, HW-NAS-Bench (Li et al., 2021) for hardware-aware NAS, and TransNAS-Bench-101 (Duan et al., 2021) for transfer learning.  ... 
arXiv:2110.10165v1 fatcat:heerfph34neyte4o73dvnvct7a

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy [article]

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, Guri Zabergja, Shakiba Moradian, Mahmoud Safari, Kaicheng Yu, Frank Hutter
2022 arXiv   pre-print
The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS).  ...  Although they have been widely adopted and used to tune real-world NAS algorithms, these benchmarks are limited to small search spaces and focus solely on image classification.  ...  HW-NAS-Bench is a NAS benchmark focusing on hardware-aware neural architecture search.  ... 
arXiv:2201.13396v2 fatcat:x5d7eug4lbexfiouvod3bsletq

Neural Architecture Search Survey: A Hardware Perspective

Krishna Teja Chitty-Venkata, Arun K. Somani
2022 ACM Computing Surveys  
We review the problem of automating hardware-aware architectural design process of Deep Neural Networks (DNNs).  ...  Hardware-Aware Neural Architecture Search (HW-NAS) automates the architectural design process of DNNs to alleviate human effort, and generate efficient models accomplishing acceptable accuracy-performance  ...  Pipeline of Hardware Aware Neural Architecture Search 3. 1 . 2 12 Hardware Aware Search Space (HW-SS).  ... 
doi:10.1145/3524500 fatcat:4ibnwmgbdnbhjpk4u7soc6aom4

Hardware-Aware Neural Architecture Search: Survey and Taxonomy

Hadjer Benmeziane, Kaoutar El Maghraoui, Hamza Ouarnoughi, Smail Niar, Martin Wistuba, Naigang Wang
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
In this survey on hardware-aware neural architecture search (HW-NAS), we present some of the existing answers proposed in the literature for the following questions: "Is it possible to build an efficient  ...  There is no doubt that making AI mainstream by bringing powerful, yet power hungry deep neural networks (DNNs) to resource-constrained devices would required an efficient co-design of algorithms, hardware  ...  A more recent paper introduced the first hardware-aware NAS benchmark, HW-NAS-Bench .  ... 
doi:10.24963/ijcai.2021/592 fatcat:322tvhnnirdernprpnahnjj75a