HM-NAS reaches 2.41% test error on CIFAR-10 with 1.8M parameters and 1.8 GPU days, and 73.4% top-1 on ImageNet, by learning hierarchical masks over a weight-sharing supernet.
Designing neural network architectures using reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
HM-NAS reaches 2.41% test error on CIFAR-10 with 1.8M parameters and 1.8 GPU days, and 73.4% top-1 on ImageNet, by learning hierarchical masks over a weight-sharing supernet.