activity
20112026
most citedUniversal approximations of permutation invariant/equivariant functions by deep neural networks

45 citations · 97 across the 32 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

math.OC2018

Bezier Simplex Fitting: Describing Pareto Fronts of Simplicial Problems with Small Samples in Multi-objective Optimization

Ken Kobayashi, Naoki Hamada, Akiyoshi Sannai +3

Multi-objective optimization problems require simultaneously optimizing two or more objective functions. Many studies have reported that the solution set of an M-objective optimiza…

stat.ML2018★ 5 cited

Reconstruction of training samples from loss functions

Akiyoshi Sannai

This paper presents a new mathematical framework to analyze the loss functions of deep neural networks with ReLU functions. Furthermore, as as application of this theory, we prove…