Zobrazeno 1 - 10
of 1 922
pro vyhledávání: '"A A, Wahib"'
Autor:
Zhuang, Chen, Chen, Peng, Liu, Xin, Yokota, Rio, Dryden, Nikoli, Endo, Toshio, Matsuoka, Satoshi, Wahib, Mohamed
Graph Convolutional Networks (GCNs) are widely used in various domains. However, training distributed full-batch GCNs on large-scale graphs poses challenges due to inefficient memory access patterns and high communication overhead. This paper present
Externí odkaz:
http://arxiv.org/abs/2411.16025
Frameworks and DSLs auto-generating code have traditionally relied on human experts developing them to have in place rigorous methods to assure the legality of the applied code transformations. Machine Learning (ML) is gaining wider adoption as a mea
Externí odkaz:
http://arxiv.org/abs/2410.03210
Autor:
Keller, Kai, Yashiro, Hisashi, Wahib, Mohamed, Gerofi, Balazs, Kestelman, Adrian Cristal, Bautista-Gomez, Leonardo
Ensemble data assimilation techniques form an indispensable part of numerical weather prediction. As the ensemble size grows and model resolution increases, the amount of required storage becomes a major issue. Data compression schemes may come to th
Externí odkaz:
http://arxiv.org/abs/2410.03184
Neural architecture search (NAS) enables re-searchers to automatically explore vast search spaces and find efficient neural networks. But NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process,
Externí odkaz:
http://arxiv.org/abs/2407.15600
Autor:
Tsaris, Aristeidis, Zhang, Chengming, Wang, Xiao, Yin, Junqi, Liu, Siyan, Ashfaq, Moetasim, Fan, Ming, Choi, Jong Youl, Wahib, Mohamed, Lu, Dan, Balaprakash, Prasanna, Wang, Feiyi
Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text has inspired scaling sequence lengths i
Externí odkaz:
http://arxiv.org/abs/2405.15780
Autor:
Zhang, Enzhi, Lyngaas, Isaac, Chen, Peng, Wang, Xiao, Igarashi, Jun, Huo, Yuankai, Wahib, Mohamed, Munetomo, Masaharu
Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a linear se
Externí odkaz:
http://arxiv.org/abs/2404.09707
This study explores the feasibility of adapting CSI-guided imaging across varied environments. Focusing on continuous model learning through continuous updates, we investigate CSI-Imager's adaptability in dynamically changing settings, specifically t
Externí odkaz:
http://arxiv.org/abs/2404.00951
Autor:
Rudi, Johann, Lee, Youngjun, Chadha, Aidan H., Wahib, Mohamed, Weide, Klaus, O'Neal, Jared P., Dubey, Anshu
CG-Kit is a new code generation toolkit that we propose as a solution for portability and maintainability for scientific computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of high-performa
Externí odkaz:
http://arxiv.org/abs/2401.03378
Autor:
Wang, Xiao, Lyngaas, Isaac, Tsaris, Aristeidis, Chen, Peng, Dash, Sajal, Shekar, Mayanka Chandra, Luo, Tao, Yoon, Hong-Jun, Wahib, Mohamed, Gouley, John
Transformer models trained on long sequences often achieve higher accuracy than short sequences. Unfortunately, conventional transformers struggle with long sequence training due to the overwhelming computation and memory requirements. Existing metho
Externí odkaz:
http://arxiv.org/abs/2311.02382
Autor:
Nguyen, Truong Thao, Gerofi, Balazs, Martinez-Noriega, Edgar Josafat, Trahay, François, Wahib, Mohamed
This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training. Using information about the loss and prediction confidence during training,
Externí odkaz:
http://arxiv.org/abs/2310.10102