Zobrazeno 1 - 10
of 704
pro vyhledávání: '"JIANG, XIAOWEN"'
In developing efficient optimization algorithms, it is crucial to account for communication constraints -- a significant challenge in modern Federated Learning. The best-known communication complexity among non-accelerated algorithms is achieved by D
Externí odkaz:
http://arxiv.org/abs/2407.07084
We present adaptive gradient methods (both basic and accelerated) for solving convex composite optimization problems in which the main part is approximately smooth (a.k.a. $(\delta, L)$-smooth) and can be accessed only via a (potentially biased) stoc
Externí odkaz:
http://arxiv.org/abs/2406.06398
Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized. The standard method, FedAvg, suffers from client drift which can hamper performance
Externí odkaz:
http://arxiv.org/abs/2404.08447
Autor:
Jiang, Xiaowen, Stich, Sebastian U.
The recently proposed stochastic Polyak stepsize (SPS) and stochastic line-search (SLS) for SGD have shown remarkable effectiveness when training over-parameterized models. However, in non-interpolation settings, both algorithms only guarantee conver
Externí odkaz:
http://arxiv.org/abs/2308.06058
Publikováno v:
IEEE Transactions on Image Processing (TIP), 2023
Halftoning aims to reproduce a continuous-tone image with pixels whose intensities are constrained to two discrete levels. This technique has been deployed on every printer, and the majority of them adopt fast methods (e.g., ordered dithering, error
Externí odkaz:
http://arxiv.org/abs/2304.12152
Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism. However, existing deep methods fail to generate halftones with a satisfying blue-noise property and require complex training
Externí odkaz:
http://arxiv.org/abs/2207.11408
Autor:
Jiang, Xiaowen, Cambareri, Valerio, Agresti, Gianluca, Ugwu, Cynthia Ifeyinwa, Simonetto, Adriano, Cardinaux, Fabien, Zanuttigh, Pietro
Sparse active illumination enables precise time-of-flight depth sensing as it maximizes signal-to-noise ratio for low power budgets. However, depth completion is required to produce dense depth maps for 3D perception. We address this task with realis
Externí odkaz:
http://arxiv.org/abs/2205.12918
Autor:
Jiang, Xiaowen, Guan, Shuyan, Chen, Linfeng, Deng, Fengxia, Yan, Hui, Liu, Fengyang, Zhai, Xuedong, Martínez-Huitle, Carlos A., Ding, Jing
Publikováno v:
In Journal of Environmental Chemical Engineering December 2024 12(6)
Publikováno v:
In Computational Biology and Chemistry December 2024 113
Autor:
Hu, Shuang, Wu, Chenghua, Li, Dan, Jiang, Xiaowen, Wang, Peng, Bi, Guofang, Ouyang, Hui, Liang, Fengting, Zhou, Wenhong, Yang, Xiao, Fang, Jian-Hong, Bi, Huichang
Publikováno v:
In Pharmacological Research December 2024 210