Faculty Introduction

SASAKI, Hiroaki

Associate Professor

Message for Students

Let's research with me if you are interested in the cutting edge technologies of machine learning and statistical data analysis.

Research Contents

Recent development of sensor systems or internet technology has led to a massive amount and diversity of data (e.g., images, sounds, etc.), and it is required to automatically find important knowledge, information and rules hidden in data. To this end, a promising technology is machine learning. In my work, novel machine learning methods are developed based on a mathematical theory. Furthermore, I am interesting in applying machine learning methods to real-world datasets as well.

Attractive Factors of My Research

I am fascinated by the high generality of machine learning: Machine learning does not focus on particular types of data, and is applicable to a variety of data. Thus, machine learning can potentially make contributions to a wide-range of research fields. Furthermore, I am very interested in developing machine learning methods through mathematical theory and modelling.


  1. Best Paper Runner-up Award, Asian Conference on Machine learning 2017
  2. Finalist for the Best Paper Award, Information-Based Induction Sciences and Machine Learning 2014
  3. Young Researcher Award, Information-Based Induction Sciences Workshop
  4. Young Researcher Award, the 22th Annual Conference of Japanese Neural Network Society

Major Books and Papers

  • Aapo Hyvärinen, Hiroaki Sasaki and Richard E. Turner, “Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning”, the 22th International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research, to appear.
  • Hiroaki Sasaki, Takafumi Kanamori, Aapo Hyvärinen, Gang Niu and Masashi Sugiyama, “Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios”, Journal of Machine Learning Research, no.180, vol.18, pp.1-47, 2018.
  • Hiroaki Sasaki, Voot Tangkaratt, Gang Niu and Masashi Sugiyama, “Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities”, Neural Computation, vol.30, no.2, pp.477-504, 2018.
  • Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno and Aapo Hyvärinen, “Simultaneous Estimation of Non-Gaussian Components and their Correlation Structure”, Neural Computation, vol.29, no.11, pp.2887-2924, 2017.
  • Hiroaki Sasaki, Yung-Kyun Noh, Gang Niu and Masashi Sugiyama, “Direct Density Derivative Estimation”, Neural Computation, vol.28, no.6, pp.1101-1140, 2016.