
Wasserstein Statistics in Onedimensional LocationScale Model
Wasserstein geometry and information geometry are two important structur...
read it

When Does Preconditioning Help or Hurt Generalization?
While second order optimizers such as natural gradient descent (NGD) oft...
read it

Wasserstein statistics in 1D locationscale model
Wasserstein geometry and information geometry are two important structur...
read it

Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective
It is known that any target function is realized in a sufficiently small...
read it

Pathological spectra of the Fisher information metric and its variants in deep neural networks
The Fisher information matrix (FIM) plays an essential role in statistic...
read it

The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks
Normalization methods play an important role in enhancing the performanc...
read it

Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
Comparing probability distributions is a fundamental problem in data sci...
read it

Fisher Information and Natural Gradient Learning of Random Deep Networks
A deep neural network is a hierarchical nonlinear model transforming inp...
read it

Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces
Statistical neurodynamics studies macroscopic behaviors of randomly conn...
read it

Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
This study analyzes the Fisher information matrix (FIM) by applying mean...
read it

Bayesian Robust Tensor Factorization for Incomplete Multiway Data
We propose a generative model for robust tensor factorization in the pre...
read it
Shunichi Amari
is this you? claim profile