Zobrazeno 1 - 10
of 1 916
pro vyhledávání: '"Chen, Zhijie"'
Combining gradient compression methods (e.g., CountSketch, quantization) and adaptive optimizers (e.g., Adam, AMSGrad) is a desirable goal in federated learning (FL), with potential benefits on both fewer communication rounds and less per-round commu
Externí odkaz:
http://arxiv.org/abs/2411.06770
Autor:
Chen, Zhijie, Zhao, Hanqing
We study the weakly coupled nonlinear Schr\"odinger system \begin{equation*} \begin{cases} -\Delta u_1 = \mu_1 u_1^{p} +\beta u_1^{\frac{p-1}{2}} u_2^{\frac{p+1}{2}}\text{ in } \Omega,\\ -\Delta u_2 = \mu_2 u_2^{p} +\beta u_2^{\frac{p-1}{2}}u_1^{\fra
Externí odkaz:
http://arxiv.org/abs/2410.22614
Autor:
Chen, Zhijie, Zhang, Xinglin
This paper proposes a novel approach for designing Single-Parameterized Kolmogorov-Arnold Networks (SKAN) by utilizing a Single-Parameterized Function (SFunc) constructed from trigonometric functions. Three new SKAN variants are developed: LSin-SKAN,
Externí odkaz:
http://arxiv.org/abs/2410.19360
Autor:
Chen, Zhijie, Zhang, Xinglin
The recently proposed Kolmogorov-Arnold Networks (KAN) networks have attracted increasing attention due to their advantage of high visualizability compared to MLP. In this paper, based on a series of small-scale experiments, we proposed the Efficient
Externí odkaz:
http://arxiv.org/abs/2410.14951
Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In this paper, we provide the first theoretical characterizations of both op
Externí odkaz:
http://arxiv.org/abs/2409.08935
Autor:
Xie, Jinheng, Mao, Weijia, Bai, Zechen, Zhang, David Junhao, Wang, Weihao, Lin, Kevin Qinghong, Gu, Yuchao, Chen, Zhijie, Yang, Zhenheng, Shou, Mike Zheng
We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of vario
Externí odkaz:
http://arxiv.org/abs/2408.12528
Autor:
Nan, Kepan, Xie, Rui, Zhou, Penghao, Fan, Tiehan, Yang, Zhenheng, Chen, Zhijie, Li, Xiang, Yang, Jian, Tai, Ying
Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previo
Externí odkaz:
http://arxiv.org/abs/2407.02371
Autor:
Chen, Zhijie, Lin, Chang-Shou
The Darboux-Treibich-Verdier (DTV) potential $\sum_{k=0}^{3}n_{k}(n_{k}+1)\wp(z+\tfrac{ \omega_{k}}{2};\tau)$ is well-known as doubly-periodic solutions of the stationary KdV hierarchy (Treibich-Verdier, Duke Math. J. {\bf 68} (1992), 217-236). In th
Externí odkaz:
http://arxiv.org/abs/2404.01879
Autor:
Chen, Anni, Luo, Hui, Chen, Zhijie, Feng, Haining, Kuang, Tengfang, An, Hui, Han, Xiang, Xiong, Wei, Xiao, Guangzong
A high-resolution displacement detection can be achieved by analyzing the scattered light of the trapping beams from the particle in optical tweezers. In some applications where trapping and displacement detection need to be separated, a detection be
Externí odkaz:
http://arxiv.org/abs/2311.06088
Autor:
Chen, Zhijie, Li, Houwang
We study the concentration phenomenon of the Lane-Emden equation with vanishing potentials \[\begin{cases} -\Delta u_n=W_n(x)u_n^{p_n},\quad u_n>0,\quad\text{in}~\Omega, u_n=0,\quad\text{on}~\partial\Omega, \int_\Omega p_n W_n(x)u_n^{p_n}dx\le C, \en
Externí odkaz:
http://arxiv.org/abs/2310.05162