Zobrazeno 1 - 10
of 5 611
pro vyhledávání: '"YUE, M."'
A key property of neural networks is their capacity of adapting to data during training. Yet, our current mathematical understanding of feature learning and its relationship to generalization remain limited. In this work, we provide a random matrix a
Externí odkaz:
http://arxiv.org/abs/2410.18938
Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a cornerstone of Tr
Externí odkaz:
http://arxiv.org/abs/2405.11751
Recent advances in machine learning have been achieved by using overparametrized models trained until near interpolation of the training data. It was shown, e.g., through the double descent phenomenon, that the number of parameters is a poor proxy fo
Externí odkaz:
http://arxiv.org/abs/2403.08160
Motivated by the recent application of approximate message passing (AMP) to the analysis of convex optimizations in multi-class classifications [Loureiro, et. al., 2021], we present a convergence analysis of AMP dynamics with non-separable multivaria
Externí odkaz:
http://arxiv.org/abs/2402.08676
Autor:
Cui, Hugo, Pesce, Luca, Dandi, Yatin, Krzakala, Florent, Lu, Yue M., Zdeborová, Lenka, Loureiro, Bruno
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9662-9695, 2024
In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we m
Externí odkaz:
http://arxiv.org/abs/2402.04980
Autor:
Eappachen, D., Jonker, P. G., Quirola-Vásquez, J., Sánchez, D. Mata, Inkenhaag, A., Levan, A. J., Fraser, M., Torres, M. A. P., Bauer, F. E., Chrimes, A. A., Stern, D., Graham, M. J., Smartt, S. J., Smith, K. W., Ravasio, M. E., Zabludoff, A. I., Yue, M., Stoppa, F., Malesani, D. B., Stone, N. C., Wen, S.
Extragalactic fast X-ray transients (FXTs) are a class of soft (0.3-10 keV) X-ray transients lasting a few hundred seconds to several hours. Several progenitor mechanisms have been suggested to produce FXTs, including supernova shock breakouts, binar
Externí odkaz:
http://arxiv.org/abs/2312.10786
We consider certain large random matrices, called random inner-product kernel matrices, which are essentially given by a nonlinear function $f$ applied entrywise to a sample-covariance matrix, $f(X^TX)$, where $X \in \mathbb{R}^{d \times N}$ is rando
Externí odkaz:
http://arxiv.org/abs/2310.18280
This paper presented a planar printed multiple-input-multiple-output (MIMO) antenna with a dimension of 100 x 45 mm 2. It composed of two crescent shaped radiators placed symmetrically with respect to the ground plane. Neutralization line applied to
Externí odkaz:
http://hdl.handle.net/10454/10738
Publikováno v:
Journal of Inflammation Research, Vol Volume 17, Pp 4129-4149 (2024)
Hui Liu,1,2 Xuan Xu,3 Ji Li,3 Zheyu Liu,1 Yuwen Xiong,1 Mengli Yue,4 Pi Liu1 1Department of Gastroenterology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, People’s Republic of China; 2Gastroenterology Insti
Externí odkaz:
https://doaj.org/article/3a85590d056a4183907510b90ff9566e
Publikováno v:
International Journal of Nanomedicine, Vol Volume 19, Pp 5227-5243 (2024)
Xuefeng Bian,1,* Ting Guo,2,* Guojie Chen,2,* Dengyun Nie,2 Miao Yue,2 Yinxing Zhu,2 Mei Lin3 1Imaging Department, The Affiliated Taizhou People’s Hospital of Nanjing Medical University, Taizhou School of Clinical Medicine, Nanjing Medi
Externí odkaz:
https://doaj.org/article/e81654ae9eee4889a9c19a4dd87c4157