Search

Your search keyword '"Zhao, Tuo"' showing total 495 results
Start Over Author "Zhao, Tuo"
495 results on '"Zhao, Tuo"'

155. Multimodal‐Synergistic‐Modulation Neuromorphic Imaging Systems for Simulating Dry Eye Imaging (Small 8/2023)

Author

Han, Xu, primary, Zhao, Xiaoli, additional, Zeng, Tao, additional, Yang, Yahan, additional, Yu, Hongyan, additional, Zhang, Cong, additional, Wang, Bin, additional, Liu, Xiaoqian, additional, Zhang, Tao, additional, Sun, Jing, additional, Li, Xinyuan, additional, Zhao, Tuo, additional, Zhang, Mingxin, additional, Ni, Yanping, additional, Tong, Yanhong, additional, Tang, Qingxin, additional, and Liu, Yichun, additional

Published
2023
Full Text
View/download PDF

161. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Author

Zhang, Qingru, Chen, Minshuo, Bukharin, Alexander, He, Pengcheng, Cheng, Yu, Chen, Weizhu, and Zhao, Tuo

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Computation and Language (cs.CL), Machine Learning (cs.LG)
Abstract

Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. However, common practice fine-tunes all of the parameters in a pre-trained model, which becomes prohibitive when a large number of downstream tasks are present. Therefore, many fine-tuning methods are proposed to learn incremental updates of pre-trained weights in a parameter efficient way, e.g., low-rank increments. These methods often evenly distribute the budget of incremental updates across all pre-trained weight matrices, and overlook the varying importance of different weight parameters. As a consequence, the fine-tuning performance is suboptimal. To bridge this gap, we propose AdaLoRA, which adaptively allocates the parameter budget among weight matrices according to their importance score. In particular, AdaLoRA parameterizes the incremental updates in the form of singular value decomposition. Such a novel approach allows us to effectively prune the singular values of unimportant updates, which is essentially to reduce their parameter budget but circumvent intensive exact SVD computations. We conduct extensive experiments with several pre-trained models on natural language processing, question answering, and natural language generation to validate the effectiveness of AdaLoRA. Results demonstrate that AdaLoRA manifests notable improvement over baselines, especially in the low budget settings. Our code is publicly available at https://github.com/QingruZhang/AdaLoRA ., The 11th International Conference on Learning Representations (ICLR 2023)

Published
2023

162. A manifold two-sample test study: integral probability metric with neural networks.

Author

Wang, Jie, Chen, Minshuo, Zhao, Tuo, Liao, Wenjing, and Xie, Yao

Subjects
ARTIFICIAL neural networks, APPROXIMATION theory, ADAPTIVE testing, INTEGRALS, DATA distribution, DIFFERENCE equations
Abstract

Two-sample tests are important areas aiming to determine whether two collections of observations follow the same distribution or not. We propose two-sample tests based on integral probability metric (IPM) for high-dimensional samples supported on a low-dimensional manifold. We characterize the properties of proposed tests with respect to the number of samples |$n$| and the structure of the manifold with intrinsic dimension |$d$|⁠. When an atlas is given, we propose a two-step test to identify the difference between general distributions, which achieves the type-II risk in the order of |$n^{-1/\max \{d,2\}}$|⁠. When an atlas is not given, we propose Hölder IPM test that applies for data distributions with |$(s,\beta)$| -Hölder densities, which achieves the type-II risk in the order of |$n^{-(s+\beta)/d}$|⁠. To mitigate the heavy computation burden of evaluating the Hölder IPM, we approximate the Hölder function class using neural networks. Based on the approximation theory of neural networks, we show that the neural network IPM test has the type-II risk in the order of |$n^{-(s+\beta)/d}$|⁠ , which is in the same order of the type-II risk as the Hölder IPM test. Our proposed tests are adaptive to low-dimensional geometric structure because their performance crucially depends on the intrinsic dimension instead of the data dimension. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

163. Multimodal‐Synergistic‐Modulation Neuromorphic Imaging Systems for Simulating Dry Eye Imaging

Author

Han, Xu, primary, Zhao, Xiaoli, additional, Zeng, Tao, additional, Yang, Yahan, additional, Yu, Hongyan, additional, Zhang, Cong, additional, Wang, Bin, additional, Liu, Xiaoqian, additional, Zhang, Tao, additional, Sun, Jing, additional, Li, Xinyuan, additional, Zhao, Tuo, additional, Zhang, Mingxin, additional, Ni, Yanping, additional, Tong, Yanhong, additional, Tang, Qingxin, additional, and Liu, Yichun, additional

Published
2022
Full Text
View/download PDF

170. A Novel Null Space-Based Kernel Discriminant Analysis for Face Recognition

Author

Zhao, Tuo, Liang, Zhizheng, Zhang, David, Liu, Yahui, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Lee, Seong-Whan, editor, and Li, Stan Z., editor

Published
2007
Full Text
View/download PDF

171. Curve Mapping Based Illumination Adjustment for Face Detection

Author

Jiang, Xiaoyue, Zhao, Tuo, Zhao, Rongchun, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Blanc-Talon, Jacques, editor, Philips, Wilfried, editor, Popescu, Dan, editor, and Scheunders, Paul, editor

Published
2006
Full Text
View/download PDF

173. Re-lighting and Compensation for Face Images

Author

Jiang, Xiaoyue, Zhao, Tuo, Xiao, Rong, Zhao, Rongchun, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Gagalowicz, André, editor, and Philips, Wilfried, editor

Published
2005
Full Text
View/download PDF

174. Framework and operation of digital twin smart freeway.

Author

Fu, Hui, Zhao, Tuo, Chen, Yanghang, Yao, Yipeng, and Leng, Jiewu

Subjects
DIGITAL twins, CITY traffic, CYBER physical systems, EXPRESS highways, INFORMATION & communication technologies
Abstract

Smart freeway is the newest form of next generation of freeway system which aims to achieve more sustainable objectives utilizing advanced information and communication technologies. Taking the advantages of digital twin on near‐real‐time interaction between the physical and cyber systems, the framework, operation, and enabled technologies of digital twin smart freeway (DTSF) are developed in this paper. A three‐layer conceptual framework is first discussed for understanding the fundamental structure, core components, and operation procedure of a DTSF system in the context of smart transportation. The key technologies of a DTSF system are also investigated, such as simulation modelling, big data analysis, intelligent prediction, and integrated freeway control. Moreover, a well‐designed case study based on Simulation of Urban Mobility (SUMO) is provided to verify the efficiency of the proposed freeway control strategy by integrating perimeter control of upstream urban network and traffic regulation of freeway segments. To the best of our knowledge, it is the first time to investigate integrated freeway control under the framework of digital twin. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

178. Self-Training with Differentiable Teacher

Author

Zuo, Simiao, primary, Yu, Yue, additional, Liang, Chen, additional, Jiang, Haoming, additional, Er, Siawpeng, additional, Zhang, Chao, additional, Zhao, Tuo, additional, and Zha, Hongyuan, additional

Published
2022
Full Text
View/download PDF

185. QUEACO

Author

Zhang, Danqing, primary, Li, Zheng, additional, Cao, Tianyu, additional, Luo, Chen, additional, Wu, Tony, additional, Lu, Hanqing, additional, Song, Yiwei, additional, Yin, Bing, additional, Zhao, Tuo, additional, and Yang, Qiang, additional

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results