-
Universal Approximation Property of Neural Ordinary Differential Equations
Neural ordinary differential equations (NODEs) is an invertible neural n...
12/04/2020 ∙ by Takeshi Teshima, et al. ∙
0
∙
share
read it
-
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
Invertible neural networks based on coupling flows (CF-INNs) have variou...
06/20/2020 ∙ by Takeshi Teshima, et al. ∙
0
∙
share
read it
-
γ-ABC: Outlier-Robust Approximate Bayesian Computation based on Robust Divergence Estimator
Making a reliable inference in complex models is an essential issue in s...
06/13/2020 ∙ by Masahiro Fujisawa, et al. ∙
0
∙
share
read it
-
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
The estimation of the ratio of two probability densities has garnered at...
06/12/2020 ∙ by Masahiro Kato, et al. ∙
0
∙
share
read it
-
Few-shot Domain Adaptation by Causal Mechanism Transfer
We study few-shot supervised domain adaptation (DA) for regression probl...
02/10/2020 ∙ by Takeshi Teshima, et al. ∙
3
∙
share
read it
-
Clipped Matrix Completion: a Remedy for Ceiling Effects
We consider the recovery of a low-rank matrix from its clipped observati...
09/13/2018 ∙ by Takeshi Teshima, et al. ∙
0
∙
share
read it
