Journal Papers (Refereed)

• Hiroaki Sasaki and Takashi Takenouchi, "Outlier-robust parameter estimation for unnormalized statistical models ", Japanese Journal of statistics and data science, accepted.

• Kaito Satta and Hiroaki Sasaki, "Graph embedding with outlier-robust ratio estimation", IEICE on Transactions on Information and Systems, no.10, vol.E105-D, pp.1812-1816, 2022.

• Hiroaki Sasaki and Takashi Takenouchi, "Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimation", Journal of Machine Learning Research, no.231, vol.23, pp.1-55, 2022.

• Qi Zhang, Hiroaki Sasaki and Kazushi Ikeda, "Direct Log-Density Gradient Estimation with Gaussian Mixture Models and its Application to Clustering", IEICE Transactions on Information and Systems, no.6, vol.E102-D, pp.1154-1162, 2019.

• 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.

• Voot Tangkaratt, Hiroaki Sasaki, and Masashi Sugiyama, "Direct Estimation of the Derivative of Quadratic Mutual Information with Application in Supervised Dimension Reduction", Neural Computation, vol.29, no.8, pp.2076-2122, 2017. 

• Ikko Yamane, Hiroaki Sasaki, and Masashi Sugiyama, "Regularized Multi-task Learning for Multi-Dimensional Log-Density Gradient Estimation", Neural Computation, vol.28, no.7, pp.1388-1410, 2016.

• Hiroaki Sasaki, Yung-Kyun Noh, Gang Niu and Masashi Sugiyama, "Direct Density Derivative Estimation", Neural Computation, vol.28, no.6, pp.1101-1140, 2016.

• Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno and Aapo Hyvärinen, "Correlated Topographic Analysis: Estimating an Ordering of Correlated Components", Machine Learning, vol.92, no.2-3, pp.285-317, 2013.

• Hiroaki Sasaki, Shunji Satoh and Shiro Usui, "Neural Implementation of Coarse-to-Fine Processing in V1 Simple Neurons", Neurocomputing, vol.73, no.4-6, pp.867-873, 2010.

• Hiroaki Sasaki and Shunji Satoh, "Super Resolution: Another Computational Role of Short-Range Horizontal Connection in the Primary Visual Cortex", Neural Networks, vol.22, no.4, pp.362-372, 2009.

International Conference Proceedings (Refereed)

• Hiroaki Sasaki, Jun-ichiro Hirayama and Takafumi Kanamori, "Mode estimation on matrix manifolds: Convergence and robustness", the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research, vol.151, pp.8056-8079, 2022. (acceptance rate: 29.2%(=492/1685))

• Hiroaki Sasaki, Tomoya Sakai and Takafumi Kanamori, "Robust Modal Regression with Direct Gradient Approximation of Modal Regression Risk", Conference on Uncertainty in Artificial Intelligence (UAI), Proceedings of Machine Learning Research, vol.124, pp.380-389, 2020. (acceptance rate: 27.6%(=142/515))

• Hiroaki Sasaki, Takashi Takenouchi, Ricardo Monti and Aapo Hyvärinen, "Robust Contrastive Learning and Nonlinear ICA in the Presence of Outliers", Conference on Uncertainty in Artificial Intelligence (UAI), Proceedings of Machine Learning Research, vol.124, pp.659-669, 2020. (acceptance rate: 27.6%(=142/515))

• 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, vol.89, pp.859-868. (oral：2.5%(=28/1111), 2019, acceptance rate：32.4%(=360/1111)).

• Kazushi Ikeda, Takatomi Kubo, Hiroaki Sasaki, Masataka Mori, Kentarou Hitomi and Kazuhito Takenaka, “Anomaly Detection of Roads from Driving Data Using a Statistical Discrepancy Measure”, Proceedings of the 21th IEEE International Conference on Intelligent Transportation Systems, pp.2064-2067, 2018. 

• Hiroaki Shiino, Hiroaki Sasaki, Gang Niu and Masashi Sugiyama, "Whitening-Free Least-Squares Non-Gaussian Component Analysis", the 9th Asian Conference on Machine learning (ACML), Proceedings of Machine Learning Research, vol.77, pp.375–390, 2017. (acceptance rate: 23.8%(= 41/172))

• Mina Ashizawa, Hiroaki Sasaki, Tomoya Sakai and Masashi Sugiyama, "Least-Squares Log-Density Gradient Clustering for Riemannian Manifolds", the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research, vol.54, pp.537–546, 2017. (acceptance rate: 31.7%(= 168/530))

• Hiroaki Sasaki, Takafumi Kanamori and Masashi Sugiyama, "Estimating Density Ridges by Direct Estimation of Density-Derivative-Ratios", the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research, vol.54, pp.204–212, 2017. (acceptance rate: 31.7%(= 168/530))

• Hiroaki Sasaki, Yurina Ono and Masashi Sugiyama, "Modal Regression via Direct Log-Density Derivative Estimation", the 23th  International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, vol.9948, pp.108-116, 2016. 

• Hiroaki Sasaki, Gang Niu and Masashi Sugiyama, "Non-Gaussian Component Analysis with Log-Density Gradient Estimation", the 19thInternational Conference on Artificial Intelligence and Statistics (AISTATS), JMLR: Workshop and Conference Proceedings, vol.51, pp.1177–1185, 2016. (acceptance rate: 30.7%(= 165/537))

• Hiroaki Sasaki, Voot Tangkaratt and Masashi Sugiyama, "Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities", the 7th Asian Conference on Machine learning (ACML), JMLR: Workshop and Conference Proceedings, vol.45, pp.33-48, 2015. (acceptance rate: 29.2%(= 28/96))

• Hiroaki Sasaki, Yung-Kyun Noh and Masashi Sugiyama, "Direct Density-Derivative Estimation and Its Application in KL-divergence Approximation", the 18th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR: Workshop and Conference Proceedings, vol. 38, pp. 809-818, 2015. (acceptance rate: 28.7%(= 127/442))

• Hiroaki Sasaki, Aapo Hyvärinen and Masashi Sugiyama, "Clustering via Mode Seeking by Direct Estimation of the Gradient of a Log-Density", the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Lecture Notes in Computer Science Part Ⅲ, vol. 8726, pp.19-34, 2014. (acceptance rate: 23.8%(= 115/483))

• Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno and Aapo Hyvärinen, "Estimating Dependency Structures for Non-Gaussian Components with Linear and Energy Correlations", the 17th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR: Workshop and Conference Proceedings, vol.33, pp.868-876, 2014. (acceptance rate: 35.8%(= 120/335))

• Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno and Aapo Hyvärinen, "Topographic Analysis of Correlated Components", the 4th Asian Conference on Machine learning (ACML), JMLR: Workshop and Conference Proceedings, vol.25, pp.365-378, 2012. (acceptance rate:  26.8%(= 37/138))

• Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno and Aapo Hyvärinen, "Learning Topographic Representations for Linearly Correlated Components", Workshop on Deep Learning and Unsupervised Feature Learning at NIPS 2011, Online Proceedings, 2011.

• Hiroaki Sasaki, Shunji Satoh and Shiro Usui, "Efficient Representation by Horizontal Connection in Primary Visual Cortex", 17th International Conference on Neural Information Processing (ICONIP), Lecture Notes in Computer Science, vol.6443, pp.132-139, 2010.

Under Review Papers / Technical Reports

• Hiroaki Sasaki and Aapo Hyvärinen, "Neural-Kernelized Conditional Density Estimation", arXiv: 1806.01754.

Awards

• Best Paper Runner-up Award, Asian Conference on Machine learning (ACML) 2017 

• Finalist of the Best Paper Award, Information-Based Induction Sciences and Machine Learning (IBISML) 2014

• Young Researcher Award, Information-Based Induction Sciences (IBIS) Workshop (IBIS 2014 若手奨励賞)

• Young Researcher Award, the 22th Annual Conference of Japanese Neural Network Society (JNNS) (JNNS 2012 大会奨励賞)