| 2021 | ICLR | When does preconditioning help or hurt generalization? | Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu |
| 2019 | AISTATS | Fisher Information and Natural Gradient Learning in Random Deep Networks. | Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi |
| 2019 | AISTATS | Interpolating between Optimal Transport and MMD using Sinkhorn Divergences. | Jean Feydy, Thibault Sjourn, Franois-Xavier Vialard, Shun-ichi Amari, Alain Trouv, Gabriel Peyr |
| 2019 | AISTATS | Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. | Ryo Karakida, Shotaro Akaho, Shun-ichi Amari |
| 2016 | ESANN | Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold. | Ryo Karakida, Masato Okada, Shun-ichi Amari |
| 2016 | ICANN | Adaptive Natural Gradient Learning Algorithms for Unnormalized Statistical Models. | Ryo Karakida, Masato Okada, Shun-ichi Amari |
| 2012 | ISIT | ℓp-constrained least squares (0 < p < 1) and its critical path. | Masahiro Yukawa, Shun-ichi Amari |
| 2011 | ISIT | Data compression in multiterminal statistical inference - linear-threshold encoding. | Shun-ichi Amari |
| 2010 | CVPR | Total Bregman divergence and its applications to shape retrieval. | Meizhu Liu, Baba C. Vemuri, Shun-ichi Amari, Frank Nielsen |
| 2010 | UC | Computations Inspired from the Brain. | Shun-ichi Amari |
| 2009 | ICASSP | State-space analysis on time-varying correlations in parallel spike sequences. | Hideaki Shimazaki, Shun-ichi Amari, Emery N. Brown, Sonja Grn |
| 2009 | ICONIP | Divergence, Optimization and Geometry. | Shun-ichi Amari |
| 2009 | ICONIP | Representative and Discriminant Feature Extraction Based on NMF for Emotion Recognition in Speech. | Dami Kim, Soo-Young Lee, Shun-ichi Amari |
| 2007 | ICASSP | Non-Negative Tensor Factorization using Alpha and Beta Divergences. | Andrzej Cichocki, Rafal Zdunek, Seungjin Choi, Robert J. Plemmons, Shun-ichi Amari |
| 2007 | ICONIP | Sparse Super Symmetric Tensor Factorization. | Andrzej Cichocki, Marko Jankovic, Rafal Zdunek, Shun-ichi Amari |
| 2007 | IJCNN | Eigenvalue Analysis on Singularity in RBF networks. | Haikun Wei, Shun-ichi Amari |
| 2007 | ISNN | The Tracking Speed of Continuous Attractors. | Si Wu, Kosuke Hamaguchi, Shun-ichi Amari |
| 2006 | ICAISC | Extended SMART Algorithms for Non-negative Matrix Factorization . | Andrzej Cichocki, Shun-ichi Amari, Rafal Zdunek, Raul Kompass, Gen Hori, Zhaoshui He |
| 2006 | ICASSP | New Algorithms for Non-Negative Matrix Factorization in Applications to Blind Source Separation. | Andrzej Cichocki, Rafal Zdunek, Shun-ichi Amari |
| 2006 | IJCNN | Online Learning Dynamics of Radial Basis Function Neural Networks near the Singularity. | Haikun Wei, Shun-ichi Amari |
| 2006 | ISNN | The Ideal Noisy Environment for Fast Neural Computation. | Si Wu, Jianfeng Feng, Shun-ichi Amari |
| 2005 | ISNN | Population Coding, Bayesian Inference and Information Geometry. | Shun-ichi Amari |
| 2004 | IJCNN | Japanese Neuroinformatics Project in Vision and RIKEN Brain Science Institute. | Shiro Usui, Shun-ichi Amari |
| 2004 | ISCAS | Beyond ICA: robust sparse signal representations. | Andrzej Cichocki, Yuanqing Li, Pando G. Georgiev, Shun-ichi Amari |
| 2003 | ESANN | On different ensembles of kernel machines. | Michiko Yamana, Hiroyuki Nakahara, Massimiliano Pontil, Shun-ichi Amari |
| 2002 | ITW | Information geometry of statistical inference - an overview. | Shun-ichi Amari |
| 2001 | IWANN | Generalization Error and Training Error at Singularities of Multilayer Perceptrons. | Shun-ichi Amari, Tomoko Ozeki, Hyeyoung Park |
| 2001 | IWANN | The Minimum Entropy and Cumulants Based Contrast Functions for Blind Source Extraction. | Sergio Cruces, Andrzej Cichocki, Shun-ichi Amari |
| 2001 | IWANN | Equi-convergence Algorithm for Blind Separation of Sources with Arbitrary Distributions. | Liqing Zhang, Shun-ichi Amari, Andrzej Cichocki |
| 2000 | ICASSP | Local stability analysis of flexible independent component analysis algorithm. | Seungjin Choi, Andrzej Cichocki, Shun-ichi Amari |
| 2000 | IJCNN | Iterative Design of Regularizers Based on Data by Minimizing Generalization Errors. | Masumi Ishikawa, Hirohito Shimada, Shun-ichi Amari |
| 2000 | IJCNN | Unfaithful Population Decoding. | Si Wu, Danmei Chen, Shun-ichi Amari |
| 2000 | PRICAI | Information Geometry of Neural Networks. | Shun-ichi Amari |
| 2000 | PRICAI | An Efficient Learning Algorithm Using Naturla Gradient and Second Order Information of Error Surface. | Hyeyoung Park, Kenji Fukumizu, Shun-ichi Amari, Yillbyung Lee |
| 1999 | ICASSP | Two spatio-temporal decorrelation learning algorithms and their application to multichannel blind deconvolution. | Seungjin Choi, Andrzej Cichocki, Shun-ichi Amari |
| 1999 | ICASSP | Adaptive paraunitary filter banks for principal and minor subspace analysis. | Scott C. Douglas, Shun-ichi Amari, Sun-Yuan Kung |
| 1998 | ICASSP | Why natural gradient? | Shun-ichi Amari, Scott C. Douglas |
| 1998 | ICONIP | Future Perspective of 'Creating Brain' Program. | Shun-ichi Amari |
| 1998 | ICONIP | Information Geometry of Neuro-Manifolds. | Shun-ichi Amari |
| 1997 | ESANN | Nonlinearity and separation capability: further justification for the ICA algorithm with mixture of densities. | Lei Xu, Chi Chiu Cheung, Jiong Ruan, Shun-ichi Amari |
| 1997 | ICASSP | Blind equalization of switching channels by ICA and learning of learning rate. | Howard Hua Yang, Shun-ichi Amari |
| 1997 | ICONIP | Non-Holonomic Constraints in Learning Blind Source Separation. | Shun-ichi Amari, Ta Chen, Andrzej Cichocki |
| 1997 | ICONIP | Annealed On-Line Learning in a Nonlinear Neural Net. | S. Bos, Shun-ichi Amari |
| 1997 | ICONIP | Natural Gradient Learning Algorithms for Decorrelation. | Seungjin Choi, Shun-ichi Amari, Andrzej Cichocki |
| 1997 | ICONIP | Adaptive Blind Deconvolution and Equalization with Self-Adaptive Nonlinearities: An Information-theoretic Approach. | Seungjin Choi, Andrzej Cichocki, Shun-ichi Amari |
| 1997 | ICONIP | Training Multi-Layer Perceptrons by Natural Gradient Descent. | H. H. Yang, Shun-ichi Amari |
| 1997 | IWANN | Statistical Analysis of Regularization Constant - From Bayes, MDL and NIC Points of View. | Shun-ichi Amari, Noboru Murata |
| 1996 | ICANN | Two Gradient Descent Algorithms for Blind Signal Separation. | Howard Hua Yang, Shun-ichi Amari |
| 1990 | ALT | Mathematical Theory of Neural Learning. | Shun-ichi Amari |
| 1990 | IJCNN | On the capacity of three-layer networks. | Shotaro Akaho, Shun-ichi Amari |
| 1979 | IJCAI | Theory of Self-Organizing Nerve Nets with Special Reference to Association and Concept Formation. | Shun-ichi Amari |