Internet Archive Scholar
Filters
























1 Hit in 0.82 sec

An Adaptive Remote Stochastic Gradient Method for Training Neural Networks [article]

Yushu Chen, Hao Jing, Wenlai Zhao, Zhiqiang Liu, Ouyi Li, Liang Qiao, Wei Xue, Guangwen Yang
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (1.8 MB)
https://web.archive.org/web/20200918161701/https://arxiv.org/pdf/1905.01422v8.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2019 pre-print
arXiv:1905.01422v5 fatcat:zuljb4iy55depcpeerchbfhptu
2019 pre-print
arXiv:1905.01422v6 fatcat:zggmjon5hrg3vcn2mqlawzu4nu
2019 pre-print
arXiv:1905.01422v3 fatcat:jpdsm6r4rfbabos3svi7qlwlre
2019 pre-print
arXiv:1905.01422v2 fatcat:rlsw4slbsbfpvif4zqcbxy7mya
2019 pre-print
arXiv:1905.01422v1 fatcat:u4cyrcxgwnepbif4bgdivqrvlu
2019 pre-print
arXiv:1905.01422v4 fatcat:agqjg2x2bnbctdn4n5ss7rfc4u
2020 pre-print
arXiv:1905.01422v7 fatcat:ofq55zrlqrbg7p52tmwutzugdq
RSG is further combined with adaptive methods to construct ARSG for acceleration. The method is efficient in computation and memory, and is straightforward to implement.  ...  In particular, for training ResNet-50 on ImageNet, ARSG outperforms ADAM in convergence speed and meanwhile it surpasses SGD in generalization.  ...  Introduction and related work First-order optimization methods e.g. [30, 28, 2, 31, 15] are competitive workhorses for training neural networks. Compared with second-order methods e.g.  ... 
arXiv:1905.01422v8 fatcat:7l5cewu2dne4rg3xujhqf3ad7q
Multiple Versions
Citation

Yushu Chen, Hao Jing, Wenlai Zhao, Zhiqiang Liu, Ouyi Li, Liang Qiao, Wei Xue, Guangwen Yang. "An Adaptive Remote Stochastic Gradient Method for Training Neural Networks." arXiv (2020)