activity
20172020
most citedInformation Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem

2 citations · 3 across the 3 of their papers we have counts for

collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2020

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry

Tomohiro Hayase, Ryo Karakida

The Fisher information matrix (FIM) is fundamental to understanding the trainability of deep neural nets (DNN), since it describes the parameter space's local metric. We investigat…

stat.ML2019

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

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…

stat.ML2018

Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach

Ryo Karakida, Shotaro Akaho, Shun-ichi Amari

The Fisher information matrix (FIM) is a fundamental quantity to represent the characteristics of a stochastic model, including deep neural networks (DNNs). The present study revea…

stat.ML2017

Concept Formation and Dynamics of Repeated Inference in Deep Generative Models

Yoshihiro Nagano, Ryo Karakida, Masato Okada

Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denois…