activity
20102022
collaborators

5 papers

cs.DM2022

Cover time of graphs with bounded genus

Naoki Matsumoto, Yuuki Takai

The cover time of a finite connected graph is the expected number of steps needed for a simple random walk on the graph to visit all vertices of the graph. It is known that the cov…

cs.LG2020

On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexity

Yuuki Takai, Akiyoshi Sannai, Matthieu Cordonnier

The classical approach to measure the expressive power of deep neural networks with piecewise linear activations is based on counting their maximum number of linear regions. This c…

cs.LG2019

Universal approximations of permutation invariant/equivariant functions by deep neural networks

Akiyoshi Sannai, Yuuki Takai, Matthieu Cordonnier

In this paper, we develop a theory about the relationship between -invariant/equivariant functions and deep neural networks for finite group . Especially, for a given -inv…

cs.DS2018

Finding Cheeger Cuts in Hypergraphs via Heat Equation

Masahiro Ikeda, Atsushi Miyauchi, Yuuki Takai +1

Cheeger's inequality states that a tightly connected subset can be extracted from a graph using an eigenvector of the normalized Laplacian associated with . More specificall…

math.NT2010

An effective isomorphy criterion for mod Galois representations

Yuuki Takai

In this paper, we consider mod Galois representations of . In particular, we obtain an effective criterion to distinguish two semisimple 2-dimensional, odd mod $…