Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
hyper-parameter_tuning [2018/09/07 14:38]
admin
hyper-parameter_tuning [2018/10/31 10:52] (current)
admin
Line 310: Line 310:
 We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.
  
 +https://​arxiv.org/​abs/​1809.04270 Rapid Training of Very Large Ensembles of Diverse Neural Networks
  
 +Our approach captures the structural similarity between members of a neural network ensemble and train it only once. Subsequently,​ this knowledge is transferred to all members of the ensemble using function-preserving transformations. Then, these ensemble networks converge significantly faster as compared to training from scratch.
 +
 +https://​arxiv.org/​abs/​1810.05749v1 Graph HyperNetworks for Neural Architecture Search
 +
 +GHNs model the topology of an architecture and therefore can predict network performance more accurately than regular hypernetworks and premature early stopping. To perform NAS, we randomly sample architectures and use the validation accuracy of networks with GHN generated weights as the surrogate search signal. GHNs are fast -- they can search nearly 10 times faster than other random search methods on CIFAR-10 and ImageNet. ​
 +
 +https://​ai.googleblog.com/​2018/​10/​introducing-adanet-fast-and-flexible.html?​m=1