464 citations · 538 across the 15 of their papers we have counts for
Showing 2019 · stat.MLShow all
2 papers · 2 filters
stat.ML2019★ 9 cited
Pathological spectra of the Fisher information metric and its variants in deep neural networks
Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
The Fisher information matrix (FIM) plays an essential role in statistics and machine learning as a Riemannian metric tensor or a component of the Hessian matrix of loss functions.…
stat.ML2019★ 8 cited
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks
Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the…