Zobrazeno 1 - 10
of 5 376
pro vyhledávání: '"low-rank decomposition"'
Autor:
Yang, Cheng, Sui, Yang, Xiao, Jinqi, Huang, Lingyi, Gong, Yu, Duan, Yuanlin, Jia, Wenqi, Yin, Miao, Cheng, Yu, Yuan, Bo
The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated paramet
Externí odkaz:
http://arxiv.org/abs/2411.01016
Autor:
Kawasaki, Airi, Nakatani, Naoki
We investigated some variational methods to compute a wavefunction based on antisymmetric product of geminals (APG). The Waring decomposition on the APG wavefunction leads a finite sum of antisymmetrized geminal power (AGP) wavefunctions, each for wh
Externí odkaz:
http://arxiv.org/abs/2410.06666
Autor:
Liu, Ruyue, Yin, Rong, Bo, Xiangzhen, Hao, Xiaoshuai, Zhou, Xingrui, Liu, Yong, Ma, Can, Wang, Weiping
Federated graph learning (FGL) has gained significant attention for enabling heterogeneous clients to process their private graph data locally while interacting with a centralized server, thus maintaining privacy. However, graph data on clients are t
Externí odkaz:
http://arxiv.org/abs/2412.13442
Deep neural networks typically impose significant computational loads and memory consumption. Moreover, the large parameters pose constraints on deploying the model on edge devices such as embedded systems. Tensor decomposition offers a clear advanta
Externí odkaz:
http://arxiv.org/abs/2408.16289
Autor:
Zhang, Stephen, Papyan, Vardan
The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory consumption and c
Externí odkaz:
http://arxiv.org/abs/2409.13652
Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications with low ari
Externí odkaz:
http://arxiv.org/abs/2405.06626
Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as personal comp
Externí odkaz:
http://arxiv.org/abs/2405.15877
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed.
Externí odkaz:
http://arxiv.org/abs/2406.19931
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.