Zobrazeno 1 - 10
of 13 930
pro vyhledávání: '"Li, Pan"'
Autor:
Chien, Eli, Li, Pan
We study the Differential Privacy (DP) guarantee of hidden-state Noisy-SGD algorithms over a bounded domain. Standard privacy analysis for Noisy-SGD assumes all internal states are revealed, which leads to a divergent R'enyi DP bound with respect to
Externí odkaz:
http://arxiv.org/abs/2410.01068
Autor:
He, Wen-Jie, Zhang, Ren-You, Han, Liang, Jiang, Yi, Li, Zhe, Wang, Xiao-Feng, Li, Shu-Xiang, Li, Pan-Feng, Wang, Qing-hai
The planar two-loop scalar Feynman integrals contributing to the massive NNLO QCD corrections for $W$-boson pair production via quark-antiquark annihilation can be classified into three family branches, each of which is reduced to a distinct set of m
Externí odkaz:
http://arxiv.org/abs/2409.08879
Autor:
Guo, Tiezheng, Wang, Chen, Liu, Yanyi, Tang, Jiawei, Li, Pan, Xu, Sai, Yang, Qingwen, Gao, Xianlin, Li, Zhi, Wen, Yingyou
Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external documents in iso
Externí odkaz:
http://arxiv.org/abs/2408.02907
Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been devoted to
Externí odkaz:
http://arxiv.org/abs/2407.20912
Autor:
Li, Pan, Li, Linfeng, Wang, Mingze, Cao, KaiMing, Gao, Ruihong, Liu, Heshan, Shi, Meng, Luo, Ziren
This paper reports the achievement of 120W single-frequency narrow linewidth 1018nm laser based on wide-tunable DBR fiber seed source. The DBR structure seed source uses 8mm long doped optical fibers with a line width of 3.25k. The wavelength tuning
Externí odkaz:
http://arxiv.org/abs/2407.19641
Autor:
Li, Pan, Tuzhilin, Alexander
Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are heterogeneous across
Externí odkaz:
http://arxiv.org/abs/2407.03580
The interpretability of machine learning models has gained increasing attention, particularly in scientific domains where high precision and accountability are crucial. This research focuses on distinguishing between two critical data patterns -- sen
Externí odkaz:
http://arxiv.org/abs/2407.00849
Graph diffusion, which iteratively propagates real-valued substances among the graph, is used in numerous graph/network-involved applications. However, releasing diffusion vectors may reveal sensitive linking information in the data such as transacti
Externí odkaz:
http://arxiv.org/abs/2407.00077
Machine learning on graphs has recently found extensive applications across domains. However, the commonly used Message Passing Neural Networks (MPNNs) suffer from limited expressive power and struggle to capture long-range dependencies. Graph transf
Externí odkaz:
http://arxiv.org/abs/2406.05815
Multiple Sequence Alignment (MSA) plays a pivotal role in unveiling the evolutionary trajectories of protein families. The accuracy of protein structure predictions is often compromised for protein sequences that lack sufficient homologous informatio
Externí odkaz:
http://arxiv.org/abs/2406.05347