Search Results for author: Takashi Takenouchi

Found 7 papers, 1 papers with code

Lower-Bounded Proper Losses for Weakly Supervised Classification

1 code implementation4 Mar 2021 Shuhei M. Yoshida, Takashi Takenouchi, Masashi Sugiyama

To this end, we derive a representation theorem for proper losses in supervised learning, which dualizes the Savage representation.

Classification General Classification +1

Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimation

no code implementations6 Jan 2021 Hiroaki Sasaki, Takashi Takenouchi

Then, we propose a practical method through outlier-robust density ratio estimation, which can be seen as performing maximization of MI, nonlinear ICA or nonlinear subspace estimation.

Contrastive Learning Density Ratio Estimation +1

Regret Minimization for Causal Inference on Large Treatment Space

no code implementations10 Jun 2020 Akira Tanimoto, Tomoya Sakai, Takashi Takenouchi, Hisashi Kashima

Predicting which action (treatment) will lead to a better outcome is a central task in decision support systems.

Causal Inference Decision Making

Robust contrastive learning and nonlinear ICA in the presence of outliers

no code implementations1 Nov 2019 Hiroaki Sasaki, Takashi Takenouchi, Ricardo Monti, Aapo Hyvärinen

We develop two robust nonlinear ICA methods based on the {\gamma}-divergence, which is a robust alternative to the KL-divergence in logistic regression.

Causal Discovery Contrastive Learning +2

Zero-shot Domain Adaptation Based on Attribute Information

no code implementations13 Mar 2019 Masato Ishii, Takashi Takenouchi, Masashi Sugiyama

In this paper, we propose a novel domain adaptation method that can be applied without target data.

Domain Adaptation

Empirical Localization of Homogeneous Divergences on Discrete Sample Spaces

no code implementations NeurIPS 2015 Takashi Takenouchi, Takafumi Kanamori

In this paper, we propose a novel parameter estimator for probabilistic models on discrete space.

Cannot find the paper you are looking for? You can Submit a new open access paper.