1. Understanding approximate Fisher information for fast convergence of natural gradient descent in wide neural networks*
2. A kronecker-factored approximate fisher matrix for convolution layers;grosse;Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48,2016
3. Optimizing neural networks with kronecker-factored approximate curvature;martens;Proceedings of The 32nd International Conference on Machine Learning,2015
4. Fast convergence of natural gradient descent for over-parameterized neural networks;zhang;Advances in neural information processing systems,2019