Zobrazeno 1 - 10
of 7 962
pro vyhledávání: '"GAO, Rui"'
Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains a significant concern, which motivates us to investigate the robustness of machine learning models. While vari
Externí odkaz:
http://arxiv.org/abs/2408.09672
We study multistage distributionally robust linear optimization, where the uncertainty set is defined as a ball of distribution centered at a scenario tree using the nested distance. The resulting minimax problem is notoriously difficult to solve due
Externí odkaz:
http://arxiv.org/abs/2407.16346
Autor:
Gao, Rui, Zhu, Miaomiao
We demonstrate the existence of branched immersed 2-spheres with prescribed mean curvature, with controlled Morse index and with arbitrary codimensions in closed Riemannian manifold $N$ admitting finite fundamental group, where $\pi_k(N) \neq 0$ and
Externí odkaz:
http://arxiv.org/abs/2407.11945
Fast convolution algorithms, including Winograd and FFT, can efficiently accelerate convolution operations in deep models. However, these algorithms depend on high-precision arithmetic to maintain inference accuracy, which conflicts with the model qu
Externí odkaz:
http://arxiv.org/abs/2407.02913
In this article, we show that for a typical non-uniformly expanding unimodal map, the unique maximizing measure of a generic Lipschitz function is supported on a periodic orbit.
Comment: 18 pages
Comment: 18 pages
Externí odkaz:
http://arxiv.org/abs/2405.18083
Graph Neural Networks (GNNs) have excelled in learning from graph-structured data, especially in understanding the relationships within a single graph, i.e., intra-graph relationships. Despite their successes, GNNs are limited by neglecting the conte
Externí odkaz:
http://arxiv.org/abs/2405.03950
We present a new framework to address the non-convex robust hypothesis testing problem, wherein the goal is to seek the optimal detector that minimizes the maximum of worst-case type-I and type-II risk functions. The distributional uncertainty sets a
Externí odkaz:
http://arxiv.org/abs/2403.14822
With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service providers and data owners, an innovative SG-ZSL paradigm is proposed in this work. SG-ZSL is designed to foster efficient
Externí odkaz:
http://arxiv.org/abs/2403.09363
Autor:
Tang, Shaojie, Miao, Penpen, Gao, Xingyu, Zhong, Yu, Zhu, Dantong, Wen, Haixing, Xu, Zhihui, Wei, Qiuyue, Yao, Hongping, Huang, Xin, Gao, Rui, Zhao, Chen, Zhou, Weihua
A method was proposed for the point cloud-based registration and image fusion between cardiac single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) and cardiac computed tomography angiograms (CTA). Firstly, the left ven
Externí odkaz:
http://arxiv.org/abs/2402.06841
Existing trajectory planning methods are struggling to handle the issue of autonomous track swinging during navigation, resulting in significant errors when reaching the destination. In this article, we address autonomous trajectory planning problems
Externí odkaz:
http://arxiv.org/abs/2402.02735