Filters








6 Hits in 2.5 sec

AutoHAS: Efficient Hyperparameter and Architecture Search [article]

Xuanyi Dong, Mingxing Tan, Adams Wei Yu, Daiyi Peng, Bogdan Gabrys, Quoc V. Le
2021 arXiv   pre-print
In this work, we propose a unified pipeline, AutoHAS, to efficiently search for both architectures and hyperparameters.  ...  In experiments, we show AutoHAS is efficient and generalizable to different search spaces, baselines and datasets.  ...  Acknowledgements We want to thank Gabriel Bender, Hanxiao Liu, Hieu Pham, Ruoming Pang, Barret Zoph and Yanqi Zhou for their help and feedback.  ... 
arXiv:2006.03656v3 fatcat:y3socjtfh5bvrpukno5kmasmwy

DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture [article]

Kaichen Zhou, Lanqing Hong, Shoukang Hu, Fengwei Zhou, Binxin Ru, Jiashi Feng, Zhenguo Li
2021 arXiv   pre-print
Automated machine learning (AutoML) usually involves several crucial components, such as Data Augmentation (DA) policy, Hyper-Parameter Optimization (HPO), and Neural Architecture Search (NAS).  ...  In view of these, we propose DHA, which achieves joint optimization of Data augmentation policy, Hyper-parameter and Architecture.  ...  Conventional neural architecture search methods perform a search over a fixed set of architecture candidates and then apply or search for a separate set of hyper-parameters when retraining the best architecture  ... 
arXiv:2109.05765v1 fatcat:chsuylzfrfeg5h5txj7xualooi

AutoML: A Survey of the State-of-the-Art [article]

Xin He, Kaiyong Zhao, Xiaowen Chu
2020 arXiv   pre-print
First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS).  ...  NAS, and joint hyperparameter and architecture optimization.  ...  Joint Hyper-parameter and Architecture Optimization Most NAS methods fix the same setting of trainingrelated hyper-parameters during the whole search stage.  ... 
arXiv:1908.00709v5 fatcat:zwlhvujqnzgxja42t2yk75bsx4

Meta-Learning of NAS for Few-shot Learning in Medical Image Applications [article]

Viet-Khoa Vo-Ho, Kashu Yamazaki, Hieu Hoang, Minh-Triet Tran, Ngan Le
2022 arXiv   pre-print
Even though it has been shown that network architecture plays a critical role in learning feature representation feature from data and the final performance, searching for the best network architecture  ...  Automated machine learning (AutoML) and its advanced techniques i.e. Neural Architecture Search (NAS) have been promoted to address those limitations.  ...  OIA-1946391; partially funded by Gia Lam Urban Development and Investment Company Limited, Vingroup and supported by Vingroup Innovation Foundation (VINIF) under project code VINIF.2019.DA19.  ... 
arXiv:2203.08951v1 fatcat:rafuwlli4reabfrygeed4e6o6y

Mixed Variable Bayesian Optimization with Frequency Modulated Kernels [article]

Changyong Oh, Efstratios Gavves, Max Welling
2021 arXiv   pre-print
On joint optimization of neural architectures and SGD hyperparameters, BO-FM outperforms competitors including Regularized evolution(RE) and BOHB.  ...  Therefore, we specify and prove conditions for FM kernels to be positive definite and to exhibit the similarity measure behavior.  ...  Xuanyi Dong, Mingxing Tan, Adams Wei Yu, Daiyi Peng, Bogdan Gabrys, and Quoc V Le. Autohas: Efficient hyperparameter and architecture search. arXiv preprint arXiv:2006.03656, 2020.  ... 
arXiv:2102.12792v1 fatcat:ptotp3bbpfcsdfceizi7donxva

AutonoML: Towards an Integrated Framework for Autonomous Machine Learning [article]

David Jacob Kedziora and Katarzyna Musial and Bogdan Gabrys
2022 arXiv   pre-print
In doing so, we survey developments in the following research areas: hyperparameter optimisation, multi-component models, neural architecture search, automated feature engineering, meta-learning, multi-level  ...  Ultimately, we conclude that the notion of architectural integration deserves more discussion, without which the field of automated ML risks stifling both its technical advantages and general uptake.  ...  Differentiable ARchiTecture Search (DARTS) is an archetype of this strategy [242] , which eschews discretisation and aims to relax network representation into a continuous space.  ... 
arXiv:2012.12600v2 fatcat:6rj4ubhcjncvddztjs7tql3itq