TY - GEN
T1 - M2SGD
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
AU - Kuo, Nicholas I.Hsien
AU - Harandi, Mehrtash
AU - Fourrier, Nicolas
AU - Walder, Christian
AU - Ferraro, Gabriela
AU - Suominen, Hanna
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7/28
Y1 - 2020/7/28
N2 - Meta-learning concerns rapid knowledge acquisition. One popular approach cast optimisation as a learning problem and it has been shown that learnt neural optimisers updated base learners more quickly than their handcrafted counterparts. In this paper, we learn an optimisation rule that sparsely updates the learner parameters and removes redundant weights. We present Masked Meta-SGD (M2SGD), a neural optimiser which is not only capable of updating learners quickly, but also capable of removing 83.71% weights for ResNet20s.We release our codes at https://github.com/Nic5472K/CLVISION2020-CVPR-M2SGD.
AB - Meta-learning concerns rapid knowledge acquisition. One popular approach cast optimisation as a learning problem and it has been shown that learnt neural optimisers updated base learners more quickly than their handcrafted counterparts. In this paper, we learn an optimisation rule that sparsely updates the learner parameters and removes redundant weights. We present Masked Meta-SGD (M2SGD), a neural optimiser which is not only capable of updating learners quickly, but also capable of removing 83.71% weights for ResNet20s.We release our codes at https://github.com/Nic5472K/CLVISION2020-CVPR-M2SGD.
UR - http://www.scopus.com/inward/record.url?scp=85090119597&partnerID=8YFLogxK
U2 - 10.1109/CVPRW50498.2020.00126
DO - 10.1109/CVPRW50498.2020.00126
M3 - Conference contribution
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 957
EP - 964
BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PB - IEEE Computer Society
Y2 - 14 June 2020 through 19 June 2020
ER -