Taiji Suzuki

Kazuyuki Aihara, Nicholas Bruchovsky, Taiji Suzuki, 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization

Taiji Suzuki, Yuri Kinoshita, 2022, ArXiv.

A Scaling Law for Syn2real Transfer: How Much Is Your Pre-training Effective?

Hiroaki Mikami, K. Fukumizu, Taiji Suzuki, 2022, ECML/PKDD.

Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods

Taiji Suzuki, Shunta Akiyama, 2022, ICLR.

Refined Generalization Analysis of Gradient Descent for Over-parameterized Two-layer Neural Networks with Smooth Activations on Classification Problems

Taiji Suzuki, Atsushi Nitanda, 2019, ArXiv.

Density Ratio Estimation in Machine Learning: Conclusions and Future Directions

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2012 .

Overview of Statistical Learning Theory(Survey, Activity Group "Machine Learning")

Taiji Suzuki, Taiji Suzuki, 2013 .

Mutual Information Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2012 .

Asian Conference on Machine Learning: Preface

Taiji Suzuki, Wee Sun Lee, Taiji Suzuki, 2019, ACML.

Bayesian optimization design for dose‐finding based on toxicity and efficacy outcomes in phase I/II clinical trials

Taiji Suzuki, Ami Takahashi, Taiji Suzuki, 2020, Pharmaceutical statistics.

A Curve Free Method based on Bayesian Optimization for Oncology Phase I Clinical Trials

Taiji Suzuki, Ami Takahashi, Taiji Suzuki, 2020 .

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

Murat A. Erdogdu, Jimmy Ba, Taiji Suzuki, 2022, NeurIPS.

An experimental study of the martensite nucleation and growth in 18/8 stainless steel

Taiji Suzuki, K. Suzuki, M. Ichihara, 1977 .

Understanding Generalization in Deep Learning via Tensor Methods

Taiji Suzuki, Furong Huang, Jingling Li, 2020, AISTATS.

Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

Taiji Suzuki, Kenta Oono, Taiji Suzuki, 2019, ICLR.

Theoretical Analysis of Density Ratio Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2010, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error

Taiji Suzuki, Hiroshi Abe, Tomoya Murata, 2018, IJCAI.

System identification and parameter estimation in mathematical medicine: examples demonstrated for prostate cancer

Kazuyuki Aihara, Taiji Suzuki, Kai Morino, 2016, Quantitative Biology.

AN ELECTRON MICROSCOPIC STUDY OF HYDROGEN EMBRITTLEMENT IN VANADIUM—II

Taiji Suzuki, S. Koike, 1981 .

Superdiffusion of hydrogen in vanadium measured by the permeation method

Taiji Suzuki, K. Furuya, M. Kano, 1988 .

Approximating Mutual Information by Maximum Likelihood Density Ratio Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2008, FSDM.

Metastable face-centred cubic phase in Mg-Pb alloys obtained by rapid cooling from the melt

Taiji Suzuki, K. Ito, H. Abe, 1970 .

Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality pdf

Taiji Suzuki, Taiji Suzuki, 2018, ICLR.

A Conjugate Property between Loss Functions and Uncertainty Sets in Classification Problems pdf

Takafumi Kanamori, Akiko Takeda, Taiji Suzuki, 2012, COLT.

Independently Interpretable Lasso for Generalized Linear Models

Taiji Suzuki, Hironori Fujisawa, Masaaki Takada, 2020, Neural Computation.

A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model

Kenji Fukumizu, Taiji Suzuki, Shaogao Lv, 2020, Comput. Stat. Data Anal..

Computational complexity of kernel-based density-ratio estimation: a condition number analysis

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2012, Machine Learning.

SpicyMKL: a fast algorithm for Multiple Kernel Learning with thousands of kernels

Taiji Suzuki, Ryota Tomioka, Ryota Tomioka, 2011, Machine Learning.

Least-Squares Independent Component Analysis

Masashi Sugiyama, Taiji Suzuki, Masashi Sugiyama, 2011, Neural Computation.

Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparsity Regularized Estimation

Masashi Sugiyama, Taiji Suzuki, Ryota Tomioka, 2009, J. Mach. Learn. Res..

Estimating Squared-Loss Mutual Information for Independent Component Analysis

Masashi Sugiyama, Taiji Suzuki, Masashi Sugiyama, 2009, ICA.

Mutual information estimation reveals global associations between stimuli and biological processes

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2009, BMC Bioinformatics.

Least-Squares Conditional Density Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2010, IEICE Trans. Inf. Syst..

Platelet-rich fibrin prepared from stored whole-blood samples

Taiji Suzuki, Kohya Uematsu, T. Kawase, 2017, International Journal of Implant Dentistry.

Orientation dependence of slip in tantalum single crystals

Taiji Suzuki, E. Kuramoto, S. Takeughi, 1972 .

Learning to estimate user interest utilizing the variational Bayes estimator

Kazuyuki Aihara, Taiji Suzuki, Hiroshi Tsujino, 2005, 5th International Conference on Intelligent Systems Design and Applications (ISDA'05).

Effects of hydrogen and deuterium on the temperature dependence of the shear constants C' of vanadium single crystals

Taiji Suzuki, M. Shino, H. Kojima, 1987 .

Response to the comment on “superdiffusion of hydrogen in vanadium measured by the permeation method”

Taiji Suzuki, M. Kano, S. Koike, 1989 .

Platelet-rich fibrin prepared from stored whole-blood samples

Taiji Suzuki, Kohya Uematsu, T. Kawase, 2017, International journal of implant dentistry.

Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network pdf

Taiji Suzuki, Taiji Suzuki, 2019, ICLR.

Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables

Taiji Suzuki, Hironori Fujisawa, Masaaki Takada, 2017, AISTATS.

Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space

Taiji Suzuki, Kazuma Tsuji, 2020, ArXiv.

Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics pdf

Taiji Suzuki, Taiji Suzuki, 2020, NeurIPS.

Gaussian process nonparametric tensor estimator and its minimax optimality

Taiji Suzuki, Nobuyuki Shimizu, Yukihiro Tagami, 2016, ICML.

Koopman-Based Bound for Generalization: New Aspect of Neural Networks Regarding Nonlinear Noise Filtering

Taiji Suzuki, Sho Sonoda, Atsushi Nitanda, 2023, ArXiv.

Convex Tensor Decomposition via Structured Schatten Norm Regularization

Taiji Suzuki, Ryota Tomioka, Ryota Tomioka, 2013, NIPS.

Fast learning rate of deep learning via a kernel perspective pdf

Taiji Suzuki, Taiji Suzuki, 2017, ArXiv.

Deep Two-way Matrix Reordering for Relational Data Analysis

Taiji Suzuki, C. Watanabe, 2021, Neural Networks.

Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2023, ICML.

Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods pdf

Taiji Suzuki, Shunta Akiyama, Taiji Suzuki, 2020, ICLR.

Convex Analysis of the Mean Field Langevin Dynamics

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2022, AISTATS.

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2022, ICLR.

Stochastic Particle Gradient Descent for Infinite Ensembles pdf

Taiji Suzuki, Atsushi Nitanda, Taiji Suzuki, 2017, ArXiv.

Generalized ridge estimator and model selection criteria in multivariate linear regression

Taiji Suzuki, Yuichi Mori, Taiji Suzuki, 2016, J. Multivar. Anal..

Relative Density-Ratio Estimation for Robust Distribution Comparison

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2011, Neural Computation.

AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network

Chihiro Watanabe, Taiji Suzuki, Taiji Suzuki, 2021, 2021 IEEE Symposium Series on Computational Intelligence (SSCI).

Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers

Taiji Suzuki, Taiji Suzuki, 2014, ICML.

Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method

Taiji Suzuki, Taiji Suzuki, 2013, ICML.

A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices

Masashi Sugiyama, Hisashi Kashima, Taiji Suzuki, 2010, ICML.

Scalable Deep Neural Networks via Low-Rank Matrix Factorization pdf

Taiji Suzuki, Atsushi Yaguchi, Akiyuki Tanizawa, 2019, ArXiv.

Statistical analysis of kernel-based least-squares density-ratio estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2012, Machine Learning.

On Prior Selection and Covariate Shift of β-Bayesian Prediction Under α-Divergence Risk

Taiji Suzuki, F. Komaki, 2010 .

Goodness-of-fit Test for Latent Block Models pdf

Taiji Suzuki, Chihiro Watanabe, Taiji Suzuki, 2019, Comput. Stat. Data Anal..

Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

Taiji Suzuki, Tomoya Murata, 2021, ICML.

Cross-domain Recommendation via Deep Domain Adaptation

Taiji Suzuki, Nobuyuki Shimizu, Yukihiro Tagami, 2018, ECIR.

Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees

Taiji Suzuki, Atsushi Nitanda, Taiji Suzuki, 2020, AISTATS.

Functional Gradient Boosting based on Residual Network Perception

Taiji Suzuki, Atsushi Nitanda, Taiji Suzuki, 2018, ICML.

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks pdf

Taiji Suzuki, Kenta Oono, Taiji Suzuki, 2020, NeurIPS.

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting

Taiji Suzuki, Shunta Akiyama, Taiji Suzuki, 2021, ICML.

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems

Taiji Suzuki, Ray Kawai, A. Takeda, 2022, 2203.10215.

Convergence rate of Bayesian tensor estimator and its minimax optimality

Taiji Suzuki, Taiji Suzuki, 2015, ICML.

Sharp characterization of optimal minibatch size for stochastic finite sum convex optimization

Taiji Suzuki, Atsushi Nitanda, Tomoya Murata, 2019, Knowledge and Information Systems.

Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks

Taiji Suzuki, Atsushi Yaguchi, Akiyuki Tanizawa, 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model

Taiji Suzuki, Taiji Suzuki, 2012, COLT.

Fast Learning Rate of Multiple Kernel Learning: Trade-Off between Sparsity and Smoothness

Masashi Sugiyama, Taiji Suzuki, Masashi Sugiyama, 2012, AISTATS.

Unifying Framework for Fast Learning Rate of Non-Sparse Multiple Kernel Learning

Taiji Suzuki, Taiji Suzuki, 2011, NIPS.

Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning

Taiji Suzuki, Nobuyuki Shimizu, Yukihiro Tagami, 2016, NIPS.

Improvement of multiple kernel learning using adaptively weighted regularization

Taiji Suzuki, Taiji Suzuki, 2013, JSIAM Lett..

Density-Difference Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2012, Neural Computation.

Tight and fast generalization error bound of graph embedding in metric space

Taiji Suzuki, K. Yamanishi, Atsushi Nitanda, 2023, ArXiv.

Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks pdf

Taiji Suzuki, Kenta Oono, Taiji Suzuki, 2019, ICML.

A Density-ratio Framework for Statistical Data Processing

Takafumi Kanamori, Liwei Wang, Masashi Sugiyama, 2009, IPSJ Trans. Comput. Vis. Appl..

Decomposable-Net: Scalable Low-Rank Compression for Neural Networks

Taiji Suzuki, Atsushi Yaguchi, Akiyuki Tanizawa, 2019, IJCAI.

Short-term local weather forecast using dense weather station by deep neural network

Taiji Suzuki, Hitoshi Hattori, Kazuo Yonekura, 2018, 2018 IEEE International Conference on Big Data (Big Data).

Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective

Taiji Suzuki, Hong Wang, Yuanbin Cao, 2023, 2306.13926.

Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error

Taiji Suzuki, So Hirai, Tomoaki Nishimura, 2018, IJCAI.

Trimmed Density Ratio Estimation

Akiko Takeda, Kenji Fukumizu, Taiji Suzuki, 2017, NIPS.

Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime

Taiji Suzuki, Atsushi Nitanda, 2020, ICLR.

Gradient Descent in RKHS with Importance Labeling pdf

Taiji Suzuki, Tomoya Murata, Taiji Suzuki, 2020, AISTATS.

Refined Generalization Analysis of Gradient Descent for Over-parameterized Two-layer Neural Networks with Smooth Activations on Classification Problems

Taiji Suzuki, Atsushi Nitanda, Geoffrey Chinot, 2019, ArXiv.

On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces

Taiji Suzuki, Satoshi Hayakawa, Taiji Suzuki, 2019, Neural Networks.

Fast generalization error bound of deep learning from a kernel perspective

Taiji Suzuki, Taiji Suzuki, 2018, AISTATS.

Conditional Density Estimation via Least-Squares Density Ratio Estimation

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2010, AISTATS.

Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search

Motoaki Kawanabe, Takafumi Kanamori, Masashi Sugiyama, 2011, Neural Networks.

Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding

Taiji Suzuki, Keizo Kato, Akira Nakagawa, 2020, ICML.

Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation

Taiji Suzuki, Tomoya Murata, Taiji Suzuki, 2018, NeurIPS.

Direct Divergence Approximation between Probability Distributions and Its Applications in Machine Learning

Takafumi Kanamori, Masashi Sugiyama, Taiji Suzuki, 2013, J. Comput. Sci. Eng..

U NDERSTANDING THE V ARIANCE C OLLAPSE OF SVGD IN H IGH D IMENSIONS

Murat A. Erdogdu, Denny Wu, Jimmy Ba, 2022 .

Learning sparse structural changes in high-dimensional Markov networks

Kenji Fukumizu, Taiji Suzuki, Song Liu, 2017, Behaviormetrika.

Understanding the Variance Collapse of SVGD in High Dimensions

Murat A. Erdogdu, Jimmy Ba, Taiji Suzuki, 2022, ICLR.

Bayesian optimization for estimating the maximum tolerated dose in Phase I clinical trials

Taiji Suzuki, Ami Takahashi, 2021, Contemporary clinical trials communications.

Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation

Masashi Sugiyama, Taiji Suzuki, Masashi Sugiyama, 2010, Neural Computation.

A Scaling Law for Synthetic-to-Real Transfer: A Measure of Pre-Training pdf

Kenji Fukumizu, Shin-ichi Maeda, Shogo Murai, 2021, ArXiv.

Accelerated Sparsified SGD with Error Feedback pdf

Taiji Suzuki, Tomoya Murata, Taiji Suzuki, 2019, ArXiv.

Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs

Taiji Suzuki, Kishan Wimalawarne, 2022, arXiv.org.

Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective

Taiji Suzuki, Hong Wang, Yuanbin Cao, 2023, ArXiv.

A goodness-of-fit test on the number of biclusters in a relational data matrix pdf

Chihiro Watanabe, Taiji Suzuki, Taiji Suzuki, 2021, Annals of the Institute of Statistical Mathematics.

Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann Machines

Taiji Suzuki, Atsushi Nitanda, Taiji Suzuki, 2017, AISTATS.

DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning

Taiji Suzuki, Tomoya Murata, 2023, ICML.

Density-Difference Estimation

Masashi Sugiyama, Taiji Suzuki, I. Takeuchi, 2012, Neural Computation.

Density Ratio Estimation in Machine Learning

Masashi Sugiyama, Taiji Suzuki, T. Kanamori, 2012 .

Learning Green's Function Efficiently Using Low-Rank Approximations

Taiji Suzuki, Kishan Wimalawarne, S. Langer, 2023, arXiv.org.

Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2023, ICLR.

Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2023, ArXiv.

Two-layer neural network on infinite-dimensional data: global optimization guarantee in the mean-field regime

Taiji Suzuki, Denny Wu, Atsushi Nitanda, 2023, NeurIPS.

Mutual information approximation via maximum likelihood estimation of density ratio

Masashi Sugiyama, Taiji Suzuki, Toshiyuki Tanaka, 2009, 2009 IEEE International Symposium on Information Theory.

MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search

Taiji Suzuki, K. Uto, K. Shinoda, 2022, IEEE International Joint Conference on Neural Network.

Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network pdf

Taiji Suzuki, Taiji Suzuki, 2019, ICLR.

Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input

Taiji Suzuki, Shokichi Takakura, 2023, ICML.

Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

Taiji Suzuki, Kenta Oono, 2019, ICLR.

Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint

Murat A. Erdogdu, Jimmy Ba, Taiji Suzuki, 2020, ICLR.

Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space

Taiji Suzuki, Kazuma Tsuji, 2020, Electronic Journal of Statistics.

Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparse Learning

Masashi Sugiyama, Taiji Suzuki, Ryota Tomioka, 2009 .

Data-Parallel Momentum Diagonal Empirical Fisher (DP-MDEF):Adaptive Gradient Method is Affected by Hessian Approximation and Multi-Class Data

Taiji Suzuki, Ryuji Sakai, Kosuke Haruki, 2022, 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA).

Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD pdf

Taiji Suzuki, Mitsuhiro Kimura, Takeshi Toda, 2019, ArXiv.