activity
20172021
most citedTransportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks

5 citations · 6 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20211 cited

Differentiable Multiple Shooting Layers

Stefano Massaroli, Michael Poli, Sho Sonoda +4

We detail a novel class of implicit neural models. Leveraging time-parallel methods for differential equations, Multiple Shooting Layers (MSLs) seek solutions of initial value prob…

cs.LG2020

Ridge Regression with Over-Parametrized Two-Layer Networks Converge to Ridgelet Spectrum

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Characterization of local minima draws much attention in theoretical studies of deep learning. In this study, we investigate the distribution of parameters in an over-parametrized…

stat.ML2019

Fast Approximation and Estimation Bounds of Kernel Quadrature for Infinitely Wide Models

Sho Sonoda

An infinitely wide model is a weighted integration of feature maps. This model excels at handling an infinite number of features, and thus it has been adopted…

stat.ML2018

The global optimum of shallow neural network is attained by ridgelet transform

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda +4

We prove that the global minimum of the backpropagation (BP) training problem of neural networks with an arbitrary nonlinear activation is given by the ridgelet transform. A series…

cs.LG20175 cited

Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks

Sho Sonoda, Noboru Murata

The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite t…