Zobrazeno 1 - 10
of 676
pro vyhledávání: '"Chen, Xiangning"'
The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the training of large neural networks. To tackle this challenge, Sharpness-Aware Minimization (S
Externí odkaz:
http://arxiv.org/abs/2310.07269
The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to detect LLM
Externí odkaz:
http://arxiv.org/abs/2305.19713
Autor:
Wei, Jerry, Hou, Le, Lampinen, Andrew, Chen, Xiangning, Huang, Da, Tay, Yi, Chen, Xinyun, Lu, Yifeng, Zhou, Denny, Ma, Tengyu, Le, Quoc V.
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuning leverages the intuition tha
Externí odkaz:
http://arxiv.org/abs/2305.08298
Autor:
Chen, Xiangning, Liang, Chen, Huang, Da, Real, Esteban, Wang, Kaiyuan, Liu, Yao, Pham, Hieu, Dong, Xuanyi, Luong, Thang, Hsieh, Cho-Jui, Lu, Yifeng, Le, Quoc V.
We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bri
Externí odkaz:
http://arxiv.org/abs/2302.06675
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers. However, the update rule o
Externí odkaz:
http://arxiv.org/abs/2203.02714
Autor:
Xu, Zehua, Zhang, Minying, Zhang, Ting, Cui, Hujun, Li, Hongping, Wang, Xu, Zhao, Xiaoheng, Chen, Xiangning, Cheng, Hanliang, Xu, Jianhe, Ding, Zhujin
Publikováno v:
In Fish and Shellfish Immunology August 2024 151
Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vision tasks without using convolutional layers. This naturally leads to
Externí odkaz:
http://arxiv.org/abs/2111.01353
Autor:
Lin, Hengxun, Cui, Liye, Chen, Yong, Yang, Yiping, Chen, Xiangning, Chisoro, Prince, Li, Xia, Blecker, Christophe, Zhang, Chunhui
Publikováno v:
In Food Chemistry 15 December 2024 461
Autor:
Xu, Chenchen, Wang, Shouwei, Bai, Jing, Chen, Xiangning, Shi, Yuxuan, Hao, Jingyi, Zhao, Bing
Publikováno v:
In Food Research International December 2024 197 Part 1
Predictor-based algorithms have achieved remarkable performance in the Neural Architecture Search (NAS) tasks. However, these methods suffer from high computation costs, as training the performance predictor usually requires training and evaluating h
Externí odkaz:
http://arxiv.org/abs/2108.08019