Koichi Tojo

According to our database, Koichi Tojo authored at least 6 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Universal Approximation Property of Invertible Neural Networks.

Isao Ishikawa, Takeshi Teshima, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

J. Mach. Learn. Res., 2023

A q-Analogue of the Family of Poincaré Distributions on the Upper Half Plane.

Koichi Tojo, Taro Yoshino

Proceedings of the Geometric Science of Information - 6th International Conference, 2023

2020

Universal Approximation Property of Neural Ordinary Differential Equations.

Takeshi Teshima, Koichi Tojo, Masahiro Ikeda, Isao Ishikawa, Kenta Oono

CoRR, 2020

An Exponential Family on the Upper Half Plane and Its Conjugate Prior.

Koichi Tojo, Taro Yoshino

Proceedings of the Geometric Structures of Statistical Physics, Information Geometry, and Learning, 2020

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators.

Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

On a Method to Construct Exponential Families by Representation Theory.

Koichi Tojo, Taro Yoshino

Proceedings of the Geometric Science of Information - 4th International Conference, 2019