activity
20182022
most citedUniversal Approximation Property of Neural Ordinary Differential Equations

20 citations · 29 across the 2 of their papers we have counts for

collaborators

7 papers

cs.LG20229 cited

Universal approximation property of invertible neural networks

Isao Ishikawa, Takeshi Teshima, Koichi Tojo +3

Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various m…

cs.LG2021

Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation

Takeshi Teshima, Masashi Sugiyama

Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowl…

cs.LG202020 cited

Universal Approximation Property of Neural Ordinary Differential Equations

Takeshi Teshima, Koichi Tojo, Masahiro Ikeda +2

Neural ordinary differential equations (NODEs) is an invertible neural network architecture promising for its free-form Jacobian and the availability of a tractable Jacobian determ…

cs.LG2020

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Takeshi Teshima, Isao Ishikawa, Koichi Tojo +3

Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirabl…

stat.ML2020

-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator

Masahiro Fujisawa, Takeshi Teshima, Issei Sato +1

Approximate Bayesian computation (ABC) is a likelihood-free inference method that has been employed in various applications. However, ABC can be sensitive to outliers if a data dis…

cs.LG2020

Few-shot Domain Adaptation by Causal Mechanism Transfer

Takeshi Teshima, Issei Sato, Masashi Sugiyama

We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of…