English
Related papers

Related papers: Robustifying DARTS by Eliminating Information Bypa…

200 papers

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable…

Machine Learning · Computer Science 2019-04-24 Hanxiao Liu , Karen Simonyan , Yiming Yang

In differentiable neural architecture search (NAS) algorithms like DARTS, the training set used to update model weight and the validation set used to update model architectures are sampled from the same data distribution. Thus, the uncommon…

Machine Learning · Computer Science 2021-12-02 Ruisi Zhang , Youwei Liang , Sai Ashish Somayajula , Pengtao Xie

Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation that leverages weight-sharing and SGD where all candidate…

Machine Learning · Computer Science 2022-01-28 Weijun Hong , Guilin Li , Weinan Zhang , Ruiming Tang , Yunhe Wang , Zhenguo Li , Yong Yu

Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Lunchen Xie , Eugenio Lomurno , Matteo Gambella , Danilo Ardagna , Manual Roveri , Matteo Matteucci , Qingjiang Shi

Recently Neural Architecture Search (NAS) has aroused great interest in both academia and industry, however it remains challenging because of its huge and non-continuous search space. Instead of applying evolutionary algorithm or…

Computer Vision and Pattern Recognition · Computer Science 2018-11-06 Xinbang Zhang , Zehao Huang , Naiyan Wang

Differentiable Architecture Search (DARTS) provides a baseline for searching effective network architectures based gradient, but it is accompanied by huge computational overhead in searching and training network architecture. Recently, many…

Machine Learning · Computer Science 2020-10-19 Zhaowen Wang , Wei Zhang , Zhiming Wang

Neural architecture search (NAS) is an approach for automatically designing a neural network architecture without human effort or expert knowledge. However, the high computational cost of NAS limits its use in commercial applications. Two…

Machine Learning · Computer Science 2021-03-11 Rei Sato , Jun Sakuma , Youhei Akimoto

While recent NAS algorithms are thousands of times faster than the pioneering works, it is often overlooked that they use fewer candidate operations, resulting in a significantly smaller search space. We present PR-DARTS, a NAS algorithm…

Machine Learning · Computer Science 2021-04-23 Kevin Alexander Laube , Andreas Zell

Adversarial robustness of deep learning models has gained much traction in the last few years. Various attacks and defenses are proposed to improve the adversarial robustness of modern-day deep learning architectures. While all these…

Machine Learning · Computer Science 2021-08-27 Chaitanya Devaguptapu , Devansh Agarwal , Gaurav Mittal , Pulkit Gopalani , Vineeth N Balasubramanian

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Patrick Glandorf , Timo Kaiser , Bodo Rosenhahn

Neural architecture search (NAS) typically consists of three main steps: training a super-network, training and evaluating sampled deep neural networks (DNNs), and training the discovered DNN. Most of the existing efforts speed up some…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Tien-Ju Yang , Yi-Lun Liao , Vivienne Sze

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

Machine Learning · Computer Science 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

Designing effective neural networks is a cornerstone of deep learning, and Neural Architecture Search (NAS) has emerged as a powerful tool for automating this process. Among the existing NAS approaches, Differentiable Architecture Search…

Machine Learning · Computer Science 2025-07-18 Pengjin Wu , Ferrante Neri , Zhenhua Feng

Neural architecture search (NAS) is proposed to automate the architecture design process and attracts overwhelming interest from both academia and industry. However, it is confronted with overfitting issue due to the high-dimensional search…

Machine Learning · Computer Science 2019-12-04 Yang Jiang , Cong Zhao , Zeyang Dou , Lei Pang

Existing neural architecture search (NAS) methods often return an architecture with good search performance but generalizes poorly to the test setting. To achieve better generalization, we propose a novel neighborhood-aware NAS formulation…

Machine Learning · Computer Science 2021-11-01 Xiaofang Wang , Shengcao Cao , Mengtian Li , Kris M. Kitani

The rapid proliferation of computing domains relying on Internet of Things (IoT) devices has created a pressing need for efficient and accurate deep-learning (DL) models that can run on low-power devices. However, traditional DL models tend…

Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the search costs of…

Machine Learning · Computer Science 2024-03-13 Zhenfeng He , Yao Shu , Zhongxiang Dai , Bryan Kian Hsiang Low

This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet…

Machine Learning · Computer Science 2021-03-17 Xiangning Chen , Ruochen Wang , Minhao Cheng , Xiaocheng Tang , Cho-Jui Hsieh

N-shot neural architecture search (NAS) exploits a supernet containing all candidate subnets for a given search space. The subnets are typically trained with a static training strategy (e.g., using the same learning rate (LR) scheduler and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Jeimin Jeon , Youngmin Oh , Junghyup Lee , Donghyeon Baek , Dohyung Kim , Chanho Eom , Bumsub Ham

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize…

Machine Learning · Computer Science 2023-04-25 Shaoyi Huang , Bowen Lei , Dongkuan Xu , Hongwu Peng , Yue Sun , Mimi Xie , Caiwen Ding
‹ Prev 1 3 4 5 6 7 10 Next ›