no code implementations • 7 Aug 2023 • Yufan Jiang, Qiaozhi He, Xiaomin Zhuang, Zhihua Wu, Kunpeng Wang, Wenlai Zhao, Guangwen Yang
Existing large language models have to run K times to generate a sequence of K tokens.
1 code implementation • 24 May 2023 • Yushu Chen, Shengzhuo Liu, Jinzhe Yang, Hao Jing, Wenlai Zhao, Guangwen Yang
In order to enhance the performance of Transformer models for long-term multivariate forecasting while minimizing computational demands, this paper introduces the Joint Time-Frequency Domain Transformer (JTFT).
no code implementations • 9 Sep 2022 • Yushu Chen, Guangwen Yang, Lu Wang, Qingzhong Gan, Haipeng Chen, Quanyong Xu
Atmospheric powered descent guidance can be solved by successive convexification; however, its onboard application is impeded by the sharp increase in computation caused by nonlinear aerodynamic forces.
no code implementations • 15 Aug 2022 • Xin Wang, Wei Xue, Yilun Han, Guangwen Yang
We develop a user-friendly platform NeuroGCM for efficiently developing hybrid modeling in climate simulation.
no code implementations • 24 Apr 2022 • Zheng Zhang, Yingsheng Ji, Jiachen Shen, Xi Zhang, Guangwen Yang
Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications.
no code implementations • NeurIPS 2020 • Zichuan Lin, Derek Yang, Li Zhao, Tao Qin, Guangwen Yang, Tie-Yan Liu
In this work, we propose a set of novel reward decomposition principles by constraining uniqueness and compactness of different state features/representations relevant to different sub-rewards.
1 code implementation • NeurIPS 2020 • Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma
When the test task distribution is different from the training task distribution, the performance may degrade significantly.
no code implementations • ICLR 2020 • Guangxiang Zhu*, Zichuan Lin*, Guangwen Yang, Chongjie Zhang
Sample efficiency has been one of the major challenges for deep reinforcement learning.
1 code implementation • 6 Feb 2020 • Mingzhen Li, Yi Liu, Xiaoyan Liu, Qingxiao Sun, Xin You, Hailong Yang, Zhongzhi Luan, Lin Gan, Guangwen Yang, Depei Qian
In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations.
1 code implementation • Geoscientific Model Development 2019 • Xiaomeng Huang, Xing Huang, Dong Wang, Qi Wu, Yi Li, Shixun Zhang, YuWen Chen, Mingqing Wang, Yuan Gao, Qiang Tang, Yue Chen, Zheng Fang, Zhenya Song, Guangwen Yang
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
no code implementations • NeurIPS 2019 • Zichuan Lin, Li Zhao, Derek Yang, Tao Qin, Guangwen Yang, Tie-Yan Liu
Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward channel.
1 code implementation • 4 May 2019 • Yushu Chen, Hao Jing, Wenlai Zhao, Zhi-Qiang Liu, Ouyi Li, Liang Qiao, Wei Xue, Guangwen Yang
RSG is further combined with adaptive methods to construct ARSG for acceleration.
no code implementations • 16 Apr 2019 • Mingzhen Li, Changxi Liu, Jianjin Liao, Xuegui Zheng, Hailong Yang, Rujun Sun, Jun Xu, Lin Gan, Guangwen Yang, Zhongzhi Luan, Depei Qian
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application portability.
no code implementations • 16 Mar 2019 • Jiarui Fang, Liandeng Li, Haohuan Fu, Jinlei Jiang, Wenlai Zhao, Conghui He, Xin You, Guangwen Yang
Second, we propose a set of optimization strategies for redesigning a variety of neural network layers based on Caffe.
no code implementations • 15 Jan 2019 • Ming-Cheng Chen, Riling Li, Lin Gan, Xiaobo Zhu, Guangwen Yang, Chao-Yang Lu, Jian-Wei Pan
We show that low-depth random quantum circuits can be efficiently simulated by a quantum teleportation-inspired algorithm.
Quantum Physics
no code implementations • ICLR 2019 • Jiarui Fang, Haohuan Fu, Guangwen Yang, Cho-Jui Hsieh
Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes.
no code implementations • 19 May 2018 • Zichuan Lin, Tianqi Zhao, Guangwen Yang, Lintao Zhang
Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN).
no code implementations • 13 Apr 2018 • Riling Li, Bujiao Wu, Mingsheng Ying, Xiaoming Sun, Guangwen Yang
We design a large-scale simulator of universal random quantum circuits, often called 'quantum supremacy circuits', and implement it on Sunway TaihuLight.
Quantum Physics
no code implementations • 11 Dec 2017 • Hao Zhang, Shizhen Xu, Graham Neubig, Wei Dai, Qirong Ho, Guangwen Yang, Eric P. Xing
Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs.