1 code implementation • 13 Dec 2023 • Jiquan Wang, Sha Zhao, Haiteng Jiang, Shijian Li, Tao Li, Gang Pan
In this paper, we introduce domain generalization into automatic sleep staging and propose the task of generalizable sleep staging which aims to improve the model generalization ability to unseen datasets.
1 code implementation • 29 Sep 2023 • Huiyuan Tian, Li Zhang, Shijian Li, Min Yao, Gang Pan
We visualize this process using feature maps, and further demonstrate the rationality and effectiveness of this design using proposed novel Fourier spectral analysis methods.
no code implementations • 9 Sep 2022 • Yan Cai, Shijian Li, Wei zhang, Hao Wu, Xu-Ri Yao, Qing Zhao
Hadamard single-pixel imaging (HSI) is an appealing imaging technique due to its features of low hardware complexity and industrial cost.
no code implementations • 15 Jun 2021 • Long Yang, Zhao Li, Zehong Hu, Shasha Ruan, Shijian Li, Gang Pan, Hongyang Chen
In this paper, we propose a Thompson Sampling algorithm for \emph{unimodal} bandits, where the expected reward is unimodal over the partially ordered arms.
no code implementations • 22 Apr 2021 • Yuxuan Chen, Li Zhang, Shijian Li, Gang Pan
Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e. g. StarCraft and poker.
1 code implementation • 16 Apr 2021 • Shijian Li, Oren Mangoubi, Lijie Xu, Tian Guo
Further, we observe that Sync-Switch achieves 3. 8% higher converged accuracy with just 1. 23X the training time compared to training with ASP.
1 code implementation • 7 Apr 2020 • Shijian Li, Robert J. Walls, Tian Guo
However, it is challenging to determine the appropriate cluster configuration---e. g., server type and number---for different training workloads while balancing the trade-offs in training time, cost, and model accuracy.
1 code implementation • 5 Dec 2019 • Matthew LeMay, Shijian Li, Tian Guo
Leveraging Perseus, we evaluated the inference throughput and cost for serving various models and demonstrated that multi-tenant model serving led to up to 12% cost reduction.
no code implementations • 31 Jul 2019 • Pablo Samuel Castro, Shijian Li, Daqing Zhang
We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance.
no code implementations • 1 Jul 2019 • Longxiang Shi, Shijian Li, Longbing Cao, Long Yang, Gang Zheng, Gang Pan
Alternatively, derivative-based methods treat the optimization process as a blackbox and show robustness and stability in learning continuous control tasks, but not data efficient in learning.
no code implementations • 17 May 2019 • Longxiang Shi, Shijian Li, Longbing Cao, Long Yang, Gang Pan
However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems.
no code implementations • 22 Mar 2019 • Li Zhang, Wei Wang, Shijian Li, Gang Pan
Experimentally, we demonstrate that the proposed Monte Carlo Neural Fictitious Self Play can converge to approximate Nash equilibrium in games with large-scale search depth while the Neural Fictitious Self Play can't.
no code implementations • 28 Feb 2019 • Shijian Li, Robert J. Walls, Lijie Xu, Tian Guo
Distributed training frameworks, like TensorFlow, have been proposed as a means to reduce the training time of deep learning models by using a cluster of GPU servers.
no code implementations • 25 Feb 2019 • Li Zhang, Weichen Shen, Shijian Li, Gang Pan
This model can have strong second order feature interactive learning ability like Field-aware Factorization Machine, on this basis, deep neural network is used for higher-order feature combination learning.
no code implementations • 21 Feb 2018 • Nan Zhou, Li Zhang, Shijian Li, Zhijian Wang
In application, we hope, the frameworks, the algorithm design as well as the experiment environment illustrated in this work, can be an incubator or a test bed for researchers and policymakers to handle the emerging algorithmic collusion.