Taiji Suzuki

According to our database, Taiji Suzuki authored at least 165 papers between 2005 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Transformers Provably Solve Parity Efficiently with Chain of Thought.

Juno Kim, Taiji Suzuki

CoRR, 2024

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent.

Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen

CoRR, 2024

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization.

Jiarui Jiang, Wei Huang, Miao Zhang, Taiji Suzuki, Liqiang Nie

CoRR, 2024

Transformers are Minimax Optimal Nonparametric In-Context Learners.

Juno Kim, Tai Nakamaki, Taiji Suzuki

CoRR, 2024

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit.

Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu

CoRR, 2024

Flow matching achieves minimax optimal convergence.

Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama

CoRR, 2024

State Space Models are Comparable to Transformers in Estimating Functions with Dynamic Smoothness.

Naoki Nishikawa, Taiji Suzuki

CoRR, 2024

Understanding Multimodal Contrastive Learning Through Pointwise Mutual Information.

Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji

CoRR, 2024

Dimensionality-Induced Information Loss of Outliers in Deep Neural Networks.

Kazuki Uematsu, Kosuke Haruki, Taiji Suzuki, Mitsuhiro Kimura, Takahiro Takimoto, Hideyuki Nakagawa

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning.

Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective.

Shokichi Takakura, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

How do Transformers Perform In-Context Autoregressive Learning ?

Michael Eli Sander, Raja Giryes, Taiji Suzuki, Mathieu Blondel, Gabriel Peyré

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mechanistic Design and Scaling of Hybrid Architectures.

Michael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli

Proceedings of the Forty-first International Conference on Machine Learning, 2024

State-Free Inference of State-Space Models: The *Transfer Function* Approach.

Rom N. Parnichkun, Stefano Massaroli, Alessandro Moro, Jimmy T. H. Smith, Ramin M. Hasani, Mathias Lechner, Qi An, Christopher Ré, Hajime Asama, Stefano Ermon, Taiji Suzuki, Michael Poli, Atsushi Yamashita

Proceedings of the Forty-first International Conference on Machine Learning, 2024

SILVER: Single-loop variance reduction and application to federated learning.

Kazusato Oko, Shunta Akiyama, Denny Wu, Tomoya Murata, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape.

Juno Kim, Taiji Suzuki

Proceedings of the Forty-first International Conference on Machine Learning, 2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization.

Yihang Chen, Fanghui Liu, Taiji Suzuki, Volkan Cevher

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples.

Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime.

Keita Suzuki, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data.

Atsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods.

Yuto Nishimura, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems.

Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory.

Wei Huang, Ye Shi, Zhongyi Cai, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Koopman-based generalization bound: New aspect for full-rank weights.

Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations.

Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Learning Green's Function Efficiently Using Low-Rank Approximations.

Kishan Wimalawarne, Taiji Suzuki, Sophie Langer

CoRR, 2023

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

Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki

CoRR, 2023

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

Taiji Suzuki, Denny Wu, Atsushi Nitanda

CoRR, 2023

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

Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki

CoRR, 2023

Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond.

Taiji Suzuki, Denny Wu, Kazusato Oko, Atsushi Nitanda

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction.

Taiji Suzuki, Denny Wu, Atsushi Nitanda

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Gradient-Based Feature Learning under Structured Data.

Alireza Mousavi Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective.

Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Neural Network Module Decomposition and Recomposition with Superimposed Masks.

Hiroaki Kingetsu, Kenichi Kobayashi, Taiji Suzuki

Proceedings of the International Joint Conference on Neural Networks, 2023

Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories.

Shuhei Nitta, Taiji Suzuki, Albert Rodríguez Mulet, Atsushi Yaguchi, Ryusuke Hirai

Proceedings of the International Conference on Machine Learning and Applications, 2023

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

Shokichi Takakura, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

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

Atsushi Suzuki, Atsushi Nitanda, Taiji Suzuki, Jing Wang, Feng Tian, Kenji Yamanishi

Proceedings of the International Conference on Machine Learning, 2023

Diffusion Models are Minimax Optimal Distribution Estimators.

Kazusato Oko, Shunta Akiyama, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

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

Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

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

Tomoya Murata, Taiji Suzuki

Proceedings of the International Conference on Machine Learning, 2023

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

Taiji Suzuki, Atsushi Nitanda, Denny Wu

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

Shunta Akiyama, Taiji Suzuki

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Deep two-way matrix reordering for relational data analysis.

Chihiro Watanabe, Taiji Suzuki

Neural Networks, 2022

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

Kishan Wimalawarne, Taiji Suzuki

CoRR, 2022

Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning.

Kazusato Oko, Shunta Akiyama, Tomoya Murata, Taiji Suzuki

CoRR, 2022

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

Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

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

Naoki Nishikawa, Taiji Suzuki, Atsushi Nitanda, Denny Wu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning.

Tomoya Murata, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Yuri Kinoshita, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search.

Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki

Proceedings of the International Joint Conference on Neural Networks, 2022

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

Chenyuan Xu, Kosuke Haruki, Taiji Suzuki, Masahiro Ozawa, Kazuki Uematsu, Ryuji Sakai

Proceedings of the 21st IEEE International Conference on Machine Learning and Applications, 2022

Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness.

Sho Okumoto, Taiji Suzuki

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu

Proceedings of the Tenth International Conference on Learning Representations, 2022

Understanding the Variance Collapse of SVGD in High Dimensions.

Jimmy Ba, Murat A. Erdogdu, Marzyeh Ghassemi, Shengyang Sun, Taiji Suzuki, Denny Wu, Tianzong Zhang

Proceedings of the Tenth International Conference on Learning Representations, 2022

Dimension-free convergence rates for gradient Langevin dynamics in RKHS.

Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Convex Analysis of the Mean Field Langevin Dynamics.

Atsushi Nitanda, Denny Wu, Taiji Suzuki

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank.

Kishan Wimalawarne, Taiji Suzuki

Proceedings of the Asian Conference on Machine Learning, 2022

2021

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

Atsushi Nitanda, Tomoya Murata, Taiji Suzuki

Knowl. Inf. Syst., 2021

Goodness-of-fit test for latent block models.

Chihiro Watanabe, Taiji Suzuki

Comput. Stat. Data Anal., 2021

Neural Network Module Decomposition and Recomposition.

Hiroaki Kingetsu, Kenichi Kobayashi, Taiji Suzuki

CoRR, 2021

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

Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi

CoRR, 2021

Adaptive and Interpretable Graph Convolution Networks Using Generalized Pagerank.

Kishan Wimalawarne, Taiji Suzuki

CoRR, 2021

Goodness-of-fit Test on the Number of Biclusters in Relational Data Matrix.

Chihiro Watanabe, Taiji Suzuki

CoRR, 2021

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

Chihiro Watanabe, Taiji Suzuki

Proceedings of the IEEE Symposium Series on Computational Intelligence, 2021

Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space.

Taiji Suzuki, Atsushi Nitanda

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis.

Atsushi Nitanda, Denny Wu, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Differentiable Multiple Shooting Layers.

Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

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

Atsushi Yaguchi, Taiji Suzuki, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

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

Akira Nakagawa, Keizo Kato, Taiji Suzuki

Proceedings of the 38th International Conference on Machine Learning, 2021

Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning.

Tomoya Murata, Taiji Suzuki

Proceedings of the 38th International Conference on Machine Learning, 2021

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

Shunta Akiyama, Taiji Suzuki

Proceedings of the 38th International Conference on Machine Learning, 2021

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

Taiji Suzuki, Shunta Akiyama

Proceedings of the 9th International Conference on Learning Representations, 2021

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

Atsushi Nitanda, Taiji Suzuki

Proceedings of the 9th International Conference on Learning Representations, 2021

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

Proceedings of the 9th International Conference on Learning Representations, 2021

Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features.

Shingo Yashima, Atsushi Nitanda, Taiji Suzuki

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Gradient Descent in RKHS with Importance Labeling.

Tomoya Murata, Taiji Suzuki

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

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

Satoshi Hayakawa, Taiji Suzuki

Neural Networks, 2020

Independently Interpretable Lasso for Generalized Linear Models.

Masaaki Takada, Taiji Suzuki, Hironori Fujisawa

Neural Comput., 2020

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

Shaogao Lv, Zengyan Fan, Heng Lian, Taiji Suzuki, Kenji Fukumizu

Comput. Stat. Data Anal., 2020

Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis.

Atsushi Nitanda, Denny Wu, Taiji Suzuki

CoRR, 2020

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

Kazuma Tsuji, Taiji Suzuki

CoRR, 2020

Neural Architecture Search Using Stable Rank of Convolutional Layers.

Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki

CoRR, 2020

Selective Inference for Latent Block Models.

Chihiro Watanabe, Taiji Suzuki

CoRR, 2020

Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error.

Yusuke Hayashi, Taiji Suzuki

CoRR, 2020

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

Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Kenta Oono, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

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

Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura

Proceedings of the 8th International Conference on Learning Representations, 2020

Graph Neural Networks Exponentially Lose Expressive Power for Node Classification.

Kenta Oono, Taiji Suzuki

Proceedings of the 8th International Conference on Learning Representations, 2020

Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint.

Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang

Proceedings of the 8th International Conference on Learning Representations, 2020

Domain Adaptation Regularization for Spectral Pruning.

Laurent Dillard, Yosuke Shinya, Taiji Suzuki

Proceedings of the 31st British Machine Vision Conference 2020, 2020

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

Atsushi Nitanda, Taiji Suzuki

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Understanding Generalization in Deep Learning via Tensor Methods.

Jingling Li, Yanchao Sun, Jiahao Su, Taiji Suzuki, Furong Huang

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Scalable Deep Neural Networks via Low-Rank Matrix Factorization.

Atsushi Yaguchi, Taiji Suzuki, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa

CoRR, 2019

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

Taiji Suzuki

CoRR, 2019

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

Kosuke Haruki, Taiji Suzuki, Yohei Hamakawa, Takeshi Toda, Ryuji Sakai, Masahiro Ozawa, Mitsuhiro Kimura

CoRR, 2019

Accelerated Sparsified SGD with Error Feedback.

Tomoya Murata, Taiji Suzuki

CoRR, 2019

On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective.

Kenta Oono, Taiji Suzuki

CoRR, 2019

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

Atsushi Nitanda, Taiji Suzuki

CoRR, 2019

Approximation and non-parametric estimation of ResNet-type convolutional neural networks.

Kenta Oono, Taiji Suzuki

Proceedings of the 36th International Conference on Machine Learning, 2019

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

Taiji Suzuki

Proceedings of the 7th International Conference on Learning Representations, 2019

Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum.

Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Cross-Domain Recommendation via Deep Domain Adaptation.

Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, Taiji Suzuki

Proceedings of the Advances in Information Retrieval, 2019

Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors.

Atsushi Nitanda, Taiji Suzuki

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Generalized ridge estimator and model selection criteria in multivariate linear regression.

Yuichi Mori, Taiji Suzuki

J. Multivar. Anal., 2018

Spectral-Pruning: Compressing deep neural network via spectral analysis.

Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura

CoRR, 2018

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

Tomoya Murata, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks.

Atsushi Yaguchi, Taiji Suzuki, Wataru Asano, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa

Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, 2018

Functional Gradient Boosting based on Residual Network Perception.

Atsushi Nitanda, Taiji Suzuki

Proceedings of the 35th International Conference on Machine Learning, 2018

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

Kazuo Yonekura, Hitoshi Hattori, Taiji Suzuki

Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2018), 2018

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

Masaaki Takada, Taiji Suzuki, Hironori Fujisawa

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

Fast generalization error bound of deep learning from a kernel perspective.

Taiji Suzuki

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models.

Atsushi Nitanda, Taiji Suzuki

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017

Stochastic Particle Gradient Descent for Infinite Ensembles.

Atsushi Nitanda, Taiji Suzuki

CoRR, 2017

Fast learning rate of deep learning via a kernel perspective.

Taiji Suzuki

CoRR, 2017

Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization.

Tomoya Murata, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Trimmed Density Ratio Estimation.

Song Liu, Akiko Takeda, Taiji Suzuki, Kenji Fukumizu

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

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

Atsushi Nitanda, Taiji Suzuki

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

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

Yoshito Hirata, Kai Morino, Taiji Suzuki, Qian Guo, Hiroshi Fukuhara, Kazuyuki Aihara

Quant. Biol., 2016

Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems.

Tomoya Murata, Taiji Suzuki

CoRR, 2016

Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning.

Taiji Suzuki, Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Structure Learning of Partitioned Markov Networks.

Song Liu, Taiji Suzuki, Masashi Sugiyama, Kenji Fukumizu

Proceedings of the 33nd International Conference on Machine Learning, 2016

Gaussian process nonparametric tensor estimator and its minimax optimality.

Heishiro Kanagawa, Taiji Suzuki, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami

Proceedings of the 33nd International Conference on Machine Learning, 2016

2015

Convergence rate of Bayesian tensor estimator and its minimax optimality.

Taiji Suzuki

Proceedings of the 32nd International Conference on Machine Learning, 2015

A Consistent Method for Graph Based Anomaly Localization.

Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, Taiji Suzuki

Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015

Support Consistency of Direct Sparse-Change Learning in Markov Networks.

Song Liu, Taiji Suzuki, Masashi Sugiyama

Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015

2014

Direct Learning of Sparse Changes in Markov Networks by Density Ratio Estimation.

Song Liu, John A. Quinn, Michael U. Gutmann, Taiji Suzuki, Masashi Sugiyama

Neural Comput., 2014

Convergence rate of Bayesian tensor estimator: Optimal rate without restricted strong convexity.

Taiji Suzuki

CoRR, 2014

Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers.

Taiji Suzuki

Proceedings of the 31th International Conference on Machine Learning, 2014

2013

Relative Density-Ratio Estimation for Robust Distribution Comparison.

Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Masashi Sugiyama

Neural Comput., 2013

Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation.

Taiji Suzuki, Masashi Sugiyama

Neural Comput., 2013

Density-Difference Estimation.

Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, Ichiro Takeuchi

Neural Comput., 2013

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

Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama

Mach. Learn., 2013

Improvement of multiple kernel learning using adaptively weighted regularization.

Taiji Suzuki

JSIAM Lett., 2013

Conjugate relation between loss functions and uncertainty sets in classification problems.

Takafumi Kanamori, Akiko Takeda, Taiji Suzuki

J. Mach. Learn. Res., 2013

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

Masashi Sugiyama, Song Liu, Marthinus Christoffel du Plessis, Masao Yamanaka, Makoto Yamada, Taiji Suzuki, Takafumi Kanamori

J. Comput. Sci. Eng., 2013

Convex Tensor Decomposition via Structured Schatten Norm Regularization.

Ryota Tomioka, Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

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

Taiji Suzuki

Proceedings of the 30th International Conference on Machine Learning, 2013

2012

f-Divergence Estimation and Two-Sample Homogeneity Test Under Semiparametric Density-Ratio Models.

Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama

IEEE Trans. Inf. Theory, 2012

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

Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama

Mach. Learn., 2012

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

Taiji Suzuki, Masashi Sugiyama

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

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

Takafumi Kanamori, Akiko Takeda, Taiji Suzuki

Proceedings of the COLT 2012, 2012

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

Taiji Suzuki

Proceedings of the COLT 2012, 2012

Density Ratio Estimation in Machine Learning.

Masashi Sugiyama, Taiji Suzuki, Takafumi Kanamori

Cambridge University Press, ISBN: 978-0-521-19017-6, 2012

2011

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

Masashi Sugiyama, Makoto Yamada, Paul von Bünau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe

Neural Networks, 2011

Least-squares two-sample test.

Masashi Sugiyama, Taiji Suzuki, Yuta Itoh, Takafumi Kanamori, Manabu Kimura

Neural Networks, 2011

Least-Squares Independent Component Analysis.

Taiji Suzuki, Masashi Sugiyama

Neural Comput., 2011

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

Taiji Suzuki, Ryota Tomioka

Mach. Learn., 2011

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

Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama

J. Mach. Learn. Res., 2011

Least-Squares Independence Test.

Masashi Sugiyama, Taiji Suzuki

IEICE Trans. Inf. Syst., 2011

Statistical Performance of Convex Tensor Decomposition.

Ryota Tomioka, Taiji Suzuki, Kohei Hayashi, Hisashi Kashima

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

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

Taiji Suzuki

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010

Conditional Density Estimation via Least-Squares Density Ratio Estimation.

Masashi Sugiyama, Ichiro Takeuchi, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Daisuke Okanohara

Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Least-Squares Conditional Density Estimation.

Masashi Sugiyama, Ichiro Takeuchi, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Daisuke Okanohara

IEICE Trans. Inf. Syst., 2010

Theoretical Analysis of Density Ratio Estimation.

Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2010

Regularization Strategies and Empirical Bayesian Learning for MKL.

Ryota Tomioka, Taiji Suzuki

CoRR, 2010

Direct Density Ratio Estimation with Dimensionality Reduction.

Masashi Sugiyama, Satoshi Hara, Paul von Bünau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe

Proceedings of the SIAM International Conference on Data Mining, 2010

A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices.

Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama, Hisashi Kashima

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

A Density-ratio Framework for Statistical Data Processing.

Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Shohei Hido, Jun Sese, Ichiro Takeuchi, Liwei Wang

IPSJ Trans. Comput. Vis. Appl., 2009

Mutual information estimation reveals global associations between stimuli and biological processes.

Taiji Suzuki, Masashi Sugiyama, Takafumi Kanamori, Jun Sese

BMC Bioinform., 2009

Mutual information approximation via maximum likelihood estimation of density ratio.

Taiji Suzuki, Masashi Sugiyama, Toshiyuki Tanaka

Proceedings of the IEEE International Symposium on Information Theory, 2009

Estimating Squared-Loss Mutual Information for Independent Component Analysis.

Taiji Suzuki, Masashi Sugiyama

Proceedings of the Independent Component Analysis and Signal Separation, 2009

2008

Approximating Mutual Information by Maximum Likelihood Density Ratio Estimation.

Taiji Suzuki, Masashi Sugiyama, Jun Sese, Takafumi Kanamori

Proceedings of the Third Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery, 2008

2005

Learning to estimate user interest utilizing the variational Bayes estimator.

Taiji Suzuki, Takamasa Koshizen, Kazuyuki Aihara, Hiroshi Tsujino

Proceedings of the Fifth International Conference on Intelligent Systems Design and Applications (ISDA 2005), 2005