Neural Architecture Search with Loss Flatness-aware Measure
Joonhyun Jeong ⋅ Joonsang Yu ⋅ Dongyoon Han ⋅ YoungJoon Yoo
2022 Poster
in
Workshop: Dynamic Neural Networks
in
Workshop: Dynamic Neural Networks
Abstract
We propose a new proxy measure for Neural Architecture Search (NAS) focusing on the flatness of loss surface. One step forward to the existing NAS studies utilizing the validation-set accuracy or angle which measures convergence speed during training, we claim that the flatness of the loss surface can be a promising proxy for predicting the generalization capability of neural network architectures.
Chat is not available.
Successful Page Load