no code implementations • 25 Apr 2024 • Yihan Zhou, Yiwen Lu, Zishuo Li, Jiaqi Yan, Yilin Mo
However, the size of the optimization problem in DeePC grows linearly with respect to the data size, which prohibits its application due to high computational costs.
no code implementations • 23 Apr 2024 • Zhen Ye, Zeqian Ju, Haohe Liu, Xu Tan, Jianyi Chen, Yiwen Lu, Peiwen Sun, Jiahao Pan, Weizhen Bian, Shulin He, Qifeng Liu, Yike Guo, Wei Xue
The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation.
no code implementations • 3 Jan 2024 • Yiwen Lu, Zhen Ye, Wei Xue, Xu Tan, Qifeng Liu, Yike Guo
The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable performances, producing natural audios with high similarity to the target timbre.
1 code implementation • 8 Dec 2023 • Yiwen Lu, Zishuo Li, Yihan Zhou, Na Li, Yilin Mo
In this paper, we introduce a new class of parameterized controllers, drawing inspiration from Model Predictive Control (MPC).
1 code implementation • 37th Conference on Neural Information Processing Systems (NeurIPS 2023) 2023 • Fangchen Yu, Runze Zhao, Zhan Shi, Yiwen Lu, Jicong Fan, Yicheng Zeng, Jianfeng Mao, Wenye Li
Secondly, we develop a series of affinity learning methods that equip the selfexpressive framework with ℓp-norm to construct an intrinsic affinity matrix with an adaptive extension.
1 code implementation • 29 Sep 2023 • Jiayun Li, Yuxiao Cheng, Yiwen Lu, Zhuofan Xia, Yilin Mo, Gao Huang
Activation functions are essential to introduce nonlinearity into neural networks, with the Rectified Linear Unit (ReLU) often favored for its simplicity and effectiveness.
no code implementations • 13 Jan 2023 • Yiwen Lu, Yilin Mo
The Linear-Quadratic Regulation (LQR) problem with unknown system parameters has been widely studied, but it has remained unclear whether $\tilde{ \mathcal{O}}(\sqrt{T})$ regret, which is the best known dependence on time, can be achieved almost surely.
no code implementations • 8 Dec 2022 • Yiwen Lu, Yilin Mo
Switching control strategies that unite a potentially high-performance but uncertified controller and a stabilizing albeit conservative controller are shown to be able to balance safety with efficiency, but have been less studied under partial observation of state.
no code implementations • 26 Oct 2022 • Yiwen Lu, Yilin Mo
We show that the switching strategy is both safe and efficient, in the sense that: 1) the linear-quadratic cost of the system is always bounded even if original uncertified controller is destabilizing; 2) in case the uncertified controller is stabilizing, the performance loss caused by switching converges super-exponentially to $0$ for Gaussian noise, while the converging polynomially for general heavy-tailed noise.
no code implementations • 18 May 2022 • Yiwen Lu, Yilin Mo
Sustained research efforts have been devoted to learning optimal controllers for linear stochastic dynamical systems with unknown parameters, but due to the corruption of noise, learned controllers are usually uncertified in the sense that they may destabilize the system.
no code implementations • 24 Mar 2021 • Yiwen Lu, Yilin Mo
This paper considers the linear-quadratic dual control problem where the system parameters need to be identified and the control objective needs to be optimized in the meantime.
no code implementations • 10 Feb 2021 • Xiaoteng Ma, Yiqin Yang, Chenghao Li, Yiwen Lu, Qianchuan Zhao, Yang Jun
Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks.