Taiji Suzuki - RankMe

282 papers A* 85A 18B 3C 7Journal 149Unranked 19

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning. CoRR Akifumi Wachi, Hirota Kinoshita, Shokichi Takakura, Rei Higuchi, Taiji Suzuki
2026	J	`jnl`	Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO. CoRR Shokichi Takakura, Akifumi Wachi, Rei Higuchi, Kohei Miyaguchi, Taiji Suzuki
2026	A*	`conf`	On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD. AAAI Tongcheng Zhang, Zhanpeng Zhou, Mingze Wang, Andi Han, Wei Huang, Taiji Suzuki, Junchi Yan
2026	J	`jnl`	On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD. CoRR Tongcheng Zhang, Zhanpeng Zhou, Mingze Wang, Andi Han, Wei Huang, Taiji Suzuki, Junchi Yan
2026	J	`jnl`	Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime. CoRR Hiroki Naganuma, Taiji Suzuki, Rio Yokota, Masahiro Nomura, Kohta Ishikawa, Ikuro Sato
2026	J	`jnl`	Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality. CoRR Ryotaro Kawata, Taiji Suzuki
2026	J	`jnl`	Zero-Flow Encoders. CoRR Yakun Wang, Leyang Wang, Song Liu, Taiji Suzuki
2025	A	`conf`	Clustered Invariant Risk Minimization. AISTATS Tomoya Murata, Atsushi Nitanda, Taiji Suzuki
2025	J	`jnl`	Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning. CoRR Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, Taiji Suzuki
2025	J	`jnl`	Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency. CoRR Naoki Nishikawa, Rei Higuchi, Taiji Suzuki
2025	A*	`conf`	Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models. ICML Rei Higuchi, Taiji Suzuki
2025	J	`jnl`	Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models. CoRR Rei Higuchi, Taiji Suzuki
2025	A*	`conf`	Direct Distributional Optimization for Provable Alignment of Diffusion Models. ICLR Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki
2025	J	`jnl`	Direct Distributional Optimization for Provable Alignment of Diffusion Models. CoRR Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki
2025	—	`conf`	Exact and Rich Feature Learning Dynamics of Two-Layer Linear Networks. CPAL Wei Huang, Wuyang Chen, Zhiqiang Xu, Zhangyang Wang, Taiji Suzuki
2025	A*	`conf`	Flow matching achieves almost minimax optimal convergence. ICLR Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama
2025	J	`jnl`	From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers. CoRR Ryotaro Kawata, Yujin Song, Alberto Bietti, Naoki Nishikawa, Taiji Suzuki, Samuel Vaiter, Denny Wu
2025	J	`jnl`	Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel. CoRR Yilan Chen, Zhichao Wang, Wei Huang, Andi Han, Taiji Suzuki, Arya Mazumdar
2025	J	`jnl`	How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime? CoRR Wei Huang, Andi Han, Yujin Song, Yilan Chen, Denny Wu, Difan Zou, Taiji Suzuki
2025	J	`jnl`	In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning. CoRR Tomoya Wakayama, Taiji Suzuki
2025	J	`jnl`	Learning Green's function efficiently using low-rank approximations. Mach. Learn. Kishan Wimalawarne, Taiji Suzuki, Sophie Langer
2025	J	`jnl`	Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning. CoRR Junsoo Oh, Wei Huang, Taiji Suzuki
2025	A*	`conf`	Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation. ICML Juno Kim, Denny Wu, Jason D. Lee, Taiji Suzuki
2025	J	`jnl`	Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation. CoRR Juno Kim, Denny Wu, Jason Lee, Taiji Suzuki
2025	A*	`conf`	Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning. ICML Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita, Naoki Nishikawa, Taiji Suzuki
2025	J	`jnl`	Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning. CoRR Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita, Naoki Nishikawa, Taiji Suzuki
2025	A*	`conf`	Nonlinear transformers can perform inference-time feature learning. ICML Naoki Nishikawa, Yujin Song, Kazusato Oko, Denny Wu, Taiji Suzuki
2025	A*	`conf`	On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent. ICLR Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen
2025	A*	`conf`	On the Role of Label Noise in the Feature Learning Process. ICML Andi Han, Wei Huang, Zhanpeng Zhou, Gang Niu, Wuyang Chen, Junchi Yan, Akiko Takeda, Taiji Suzuki
2025	J	`jnl`	On the Role of Label Noise in the Feature Learning Process. CoRR Andi Han, Wei Huang, Zhanpeng Zhou, Gang Niu, Wuyang Chen, Junchi Yan, Akiko Takeda, Taiji Suzuki
2025	A*	`conf`	Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression. ICLR Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li
2025	J	`jnl`	Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression. CoRR Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li
2025	A*	`conf`	Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble. ICML Atsushi Nitanda, Anzelle Lee, Damian Tan Xing Kai, Mizuki Sakaguchi, Taiji Suzuki
2025	J	`jnl`	Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble. CoRR Atsushi Nitanda, Anzelle Lee, Damian Tan Xing Kai, Mizuki Sakaguchi, Taiji Suzuki
2025	J	`jnl`	Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training. CoRR Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang, Taiji Suzuki
2025	A*	`conf`	Provable In-Context Vector Arithmetic via Retrieving Task Concepts. ICML Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, Taiji Suzuki
2025	J	`jnl`	Provable In-Context Vector Arithmetic via Retrieving Task Concepts. CoRR Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, Taiji Suzuki
2025	A*	`conf`	Quantifying Memory Utilization with Effective State-Size. ICML Rom N. Parnichkun, Neehal Tumma, Armin W. Thomas, Alessandro Moro, Qi An, Taiji Suzuki, Atsushi Yamashita, Michael Poli, Stefano Massaroli
2025	J	`jnl`	Quantifying Memory Utilization with Effective State-Size. CoRR Rom N. Parnichkun, Neehal Tumma, Armin W. Thomas, Alessandro Moro, Qi An, Taiji Suzuki, Atsushi Yamashita, Michael Poli, Stefano Massaroli
2025	A	`conf`	Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons. AISTATS Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki
2025	J	`jnl`	Sliding Window Recurrences for Sequence Models. CoRR Dragos Secrieru, Garyk Brixi, Yoshua Bengio, Taiji Suzuki, Michael Poli, Stefano Massaroli
2025	A*	`conf`	State Space Models are Provably Comparable to Transformers in Dynamic Token Selection. ICLR Naoki Nishikawa, Taiji Suzuki
2025	J	`jnl`	Test time training enhances in-context learning of nonlinear functions. CoRR Kento Kuwataka, Taiji Suzuki
2025	J	`jnl`	Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization. CoRR Zonghao Chen, Atsushi Nitanda, Arthur Gretton, Taiji Suzuki
2025	J	`jnl`	Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression. CoRR Jiarui Jiang, Wei Huang, Miao Zhang, Taiji Suzuki, Liqiang Nie
2025	A*	`conf`	Transformers Provably Solve Parity Efficiently with Chain of Thought. ICLR Juno Kim, Taiji Suzuki
2025	A*	`conf`	Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric. ICLR Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji
2025	J	`jnl`	When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars. CoRR Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa, Kazusato Oko, Shoichiro Yamaguchi, Sosuke Kobayashi, Seiya Tokui, Kohei Hayashi, Daisuke Okanohara, Taiji Suzuki
2024	—	`conf`	Dimensionality-Induced Information Loss of Outliers in Deep Neural Networks. ECML/PKDD (1) Kazuki Uematsu, Kosuke Haruki, Taiji Suzuki, Mitsuhiro Kimura, Takahiro Takimoto, Hideyuki Nakagawa
2024	J	`jnl`	Dimensionality-induced information loss of outliers in deep neural networks. CoRR Kazuki Uematsu, Kosuke Haruki, Taiji Suzuki, Mitsuhiro Kimura, Takahiro Takimoto, Hideyuki Nakagawa
2024	J	`jnl`	Flow matching achieves minimax optimal convergence. CoRR Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama
2024	C	`conf`	Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs. ICMLA Kishan Wimalawarne, Taro Sawaki, Motokiyo Hirayama, Takanobu Kawahara, Taiji Suzuki
2024	A*	`conf`	High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization. ICML Yihang Chen, Fanghui Liu, Taiji Suzuki, Volkan Cevher
2024	J	`jnl`	High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization. CoRR Yihang Chen, Fanghui Liu, Taiji Suzuki, Volkan Cevher
2024	A*	`conf`	How do Transformers Perform In-Context Autoregressive Learning ? ICML Michael Eli Sander, Raja Giryes, Taiji Suzuki, Mathieu Blondel, Gabriel Peyré
2024	J	`jnl`	How do Transformers perform In-Context Autoregressive Learning? CoRR Michael E. Sander, Raja Giryes, Taiji Suzuki, Mathieu Blondel, Gabriel Peyré
2024	A*	`conf`	Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data. ICLR Atsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu
2024	A*	`conf`	Koopman-based generalization bound: New aspect for full-rank weights. ICLR Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki
2024	A*	`conf`	Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations. COLT Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
2024	J	`jnl`	Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations. CoRR Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
2024	A*	`conf`	Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning. ICML Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki
2024	A*	`conf`	Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective. ICML Shokichi Takakura, Taiji Suzuki
2024	J	`jnl`	Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective. CoRR Shokichi Takakura, Taiji Suzuki
2024	A*	`conf`	Mechanistic Design and Scaling of Hybrid Architectures. ICML Michael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian L. Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli
2024	J	`jnl`	Mechanistic Design and Scaling of Hybrid Architectures. CoRR Michael Poli, Armin W. Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian L. Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli
2024	A*	`conf`	Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods. ICLR Yuto Nishimura, Taiji Suzuki
2024	A*	`conf`	Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. NeurIPS Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu
2024	J	`jnl`	Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. CoRR Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu
2024	A*	`conf`	On the Comparison between Multi-modal and Single-modal Contrastive Learning. NeurIPS Wei Huang, Andi Han, Yongqiang Chen, Yuan Cao, Zhiqiang Xu, Taiji Suzuki
2024	J	`jnl`	On the Comparison between Multi-modal and Single-modal Contrastive Learning. CoRR Wei Huang, Andi Han, Yongqiang Chen, Yuan Cao, Zhiqiang Xu, Taiji Suzuki
2024	J	`jnl`	On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent. CoRR Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen
2024	A*	`conf`	Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime. ICLR Keita Suzuki, Taiji Suzuki
2024	A*	`conf`	Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context. NeurIPS Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
2024	J	`jnl`	Pretrained transformer efficiently learns low-dimensional target functions in-context. CoRR Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
2024	A*	`conf`	Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples. ICML Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong
2024	J	`jnl`	Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples. CoRR Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong
2024	A*	`conf`	Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning. NeurIPS Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong
2024	J	`jnl`	Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning. CoRR Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong
2024	A*	`conf`	SILVER: Single-loop variance reduction and application to federated learning. ICML Kazusato Oko, Shunta Akiyama, Denny Wu, Tomoya Murata, Taiji Suzuki
2024	J	`jnl`	State Space Models are Comparable to Transformers in Estimating Functions with Dynamic Smoothness. CoRR Naoki Nishikawa, Taiji Suzuki
2024	A*	`conf`	State-Free Inference of State-Space Models: The Transfer Function Approach. ICML 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
2024	J	`jnl`	State-Free Inference of State-Space Models: The Transfer Function Approach. CoRR 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, Atsushi Yamashita, Michael Poli
2024	A*	`conf`	Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems. ICLR Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki
2024	A*	`conf`	Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape. ICML Juno Kim, Taiji Suzuki
2024	J	`jnl`	Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape. CoRR Juno Kim, Taiji Suzuki
2024	J	`jnl`	Transformers Provably Solve Parity Efficiently with Chain of Thought. CoRR Juno Kim, Taiji Suzuki
2024	A*	`conf`	Transformers are Minimax Optimal Nonparametric In-Context Learners. NeurIPS Juno Kim, Tai Nakamaki, Taiji Suzuki
2024	J	`jnl`	Transformers are Minimax Optimal Nonparametric In-Context Learners. CoRR Juno Kim, Tai Nakamaki, Taiji Suzuki
2024	A*	`conf`	Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory. ICLR Wei Huang, Ye Shi, Zhongyi Cai, Taiji Suzuki
2024	J	`jnl`	Understanding Multimodal Contrastive Learning Through Pointwise Mutual Information. CoRR Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji
2024	A*	`conf`	Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization. NeurIPS Jiarui Jiang, Wei Huang, Miao Zhang, Taiji Suzuki, Liqiang Nie
2024	J	`jnl`	Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization. CoRR Jiarui Jiang, Wei Huang, Miao Zhang, Taiji Suzuki, Liqiang Nie
2023	A*	`conf`	Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input. ICML Shokichi Takakura, Taiji Suzuki
2023	J	`jnl`	Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input. CoRR Shokichi Takakura, Taiji Suzuki
2023	J	`jnl`	Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction. CoRR Taiji Suzuki, Denny Wu, Atsushi Nitanda
2023	A*	`conf`	DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning. ICML Tomoya Murata, Taiji Suzuki
2023	J	`jnl`	DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning. CoRR Tomoya Murata, Taiji Suzuki
2023	A*	`conf`	Diffusion Models are Minimax Optimal Distribution Estimators. ICML Kazusato Oko, Shunta Akiyama, Taiji Suzuki
2023	J	`jnl`	Diffusion Models are Minimax Optimal Distribution Estimators. CoRR Kazusato Oko, Shunta Akiyama, Taiji Suzuki
2023	A*	`conf`	Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods. ICLR Shunta Akiyama, Taiji Suzuki
2023	A*	`conf`	Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond. NeurIPS Taiji Suzuki, Denny Wu, Kazusato Oko, Atsushi Nitanda
2023	A*	`conf`	Gradient-Based Feature Learning under Structured Data. NeurIPS Alireza Mousavi Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu
2023	J	`jnl`	Gradient-Based Feature Learning under Structured Data. CoRR Alireza Mousavi Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu
2023	J	`jnl`	Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective. CoRR Wei Huang, Yuan Cao, Haonan Wang, Xin Cao, Taiji Suzuki
2023	J	`jnl`	Koopman-Based Bound for Generalization: New Aspect of Neural Networks Regarding Nonlinear Noise Filtering. CoRR Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki
2023	J	`jnl`	Learning Green's Function Efficiently Using Low-Rank Approximations. CoRR Kishan Wimalawarne, Taiji Suzuki, Sophie Langer
2023	A*	`conf`	Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective. NeurIPS Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu
2023	A*	`conf`	Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction. NeurIPS Taiji Suzuki, Denny Wu, Atsushi Nitanda
2023	B	`conf`	Neural Network Module Decomposition and Recomposition with Superimposed Masks. IJCNN Hiroaki Kingetsu, Kenichi Kobayashi, Taiji Suzuki
2023	A*	`conf`	Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems. ICML Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki
2023	J	`jnl`	Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems. CoRR Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki
2023	C	`conf`	Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories. ICMLA Shuhei Nitta, Taiji Suzuki, Albert Rodríguez Mulet, Atsushi Yaguchi, Ryusuke Hirai
2023	J	`jnl`	Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories. CoRR Shuhei Nitta, Taiji Suzuki, Albert Rodríguez Mulet, Atsushi Yaguchi, Ryusuke Hirai
2023	A*	`conf`	Tight and fast generalization error bound of graph embedding in metric space. ICML Atsushi Suzuki, Atsushi Nitanda, Taiji Suzuki, Jing Wang, Feng Tian, Kenji Yamanishi
2023	J	`jnl`	Tight and fast generalization error bound of graph embedding in metric space. CoRR Atsushi Suzuki, Atsushi Nitanda, Taiji Suzuki, Jing Wang, Feng Tian, Kenji Yamanishi
2023	A*	`conf`	Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics. ICLR Taiji Suzuki, Atsushi Nitanda, Denny Wu
2022	—	`conf`	A Scaling Law for Syn2real Transfer: How Much Is Your Pre-training Effective? ECML/PKDD (3) Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi
2022	A	`conf`	Convex Analysis of the Mean Field Langevin Dynamics. AISTATS Atsushi Nitanda, Denny Wu, Taiji Suzuki
2022	J	`jnl`	Convex Analysis of the Mean Field Langevin Dynamics. CoRR Atsushi Nitanda, Denny Wu, Taiji Suzuki
2022	C	`conf`	Data-Parallel Momentum Diagonal Empirical Fisher (DP-MDEF):Adaptive Gradient Method is Affected by Hessian Approximation and Multi-Class Data. ICMLA Chenyuan Xu, Kosuke Haruki, Taiji Suzuki, Masahiro Ozawa, Kazuki Uematsu, Ryuji Sakai
2022	J	`jnl`	Deep two-way matrix reordering for relational data analysis. Neural Networks Chihiro Watanabe, Taiji Suzuki
2022	A*	`conf`	Dimension-free convergence rates for gradient Langevin dynamics in RKHS. COLT Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki
2022	A*	`conf`	Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning. NeurIPS Tomoya Murata, Taiji Suzuki
2022	J	`jnl`	Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning. CoRR Tomoya Murata, Taiji Suzuki
2022	J	`jnl`	Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods. CoRR Shunta Akiyama, Taiji Suzuki
2022	J	`jnl`	Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs. CoRR Kishan Wimalawarne, Taiji Suzuki
2022	A*	`conf`	High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation. NeurIPS Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
2022	J	`jnl`	High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation. CoRR Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
2022	A*	`conf`	Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization. NeurIPS Yuri Kinoshita, Taiji Suzuki
2022	J	`jnl`	Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization. CoRR Yuri Kinoshita, Taiji Suzuki
2022	C	`conf`	Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank. ACML Kishan Wimalawarne, Taiji Suzuki
2022	A*	`conf`	Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness. ICLR Sho Okumoto, Taiji Suzuki
2022	B	`conf`	MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search. IJCNN Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki
2022	A*	`conf`	Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization. ICLR Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu
2022	A*	`conf`	Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime. NeurIPS Naoki Nishikawa, Taiji Suzuki, Atsushi Nitanda, Denny Wu
2022	A*	`conf`	Understanding the Variance Collapse of SVGD in High Dimensions. ICLR Jimmy Ba, Murat A. Erdogdu, Marzyeh Ghassemi, Shengyang Sun, Taiji Suzuki, Denny Wu, Tianzong Zhang
2022	J	`jnl`	Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning. CoRR Kazusato Oko, Shunta Akiyama, Tomoya Murata, Taiji Suzuki
2021	J	`jnl`	A Scaling Law for Synthetic-to-Real Transfer: A Measure of Pre-Training. CoRR Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi
2021	J	`jnl`	Adaptive and Interpretable Graph Convolution Networks Using Generalized Pagerank. CoRR Kishan Wimalawarne, Taiji Suzuki
2021	—	`conf`	AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network. SSCI Chihiro Watanabe, Taiji Suzuki
2021	J	`jnl`	AutoLL: Automatic Linear Layout of Graphs based on Deep Neural Network. CoRR Chihiro Watanabe, Taiji Suzuki
2021	A*	`conf`	Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods. ICLR Taiji Suzuki, Shunta Akiyama
2021	A*	`conf`	Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning. ICML Tomoya Murata, Taiji Suzuki
2021	J	`jnl`	Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning. CoRR Tomoya Murata, Taiji Suzuki
2021	A*	`conf`	Decomposable-Net: Scalable Low-Rank Compression for Neural Networks. IJCAI Atsushi Yaguchi, Taiji Suzuki, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa
2021	J	`jnl`	Deep Two-way Matrix Reordering for Relational Data Analysis. CoRR Chihiro Watanabe, Taiji Suzuki
2021	A*	`conf`	Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space. NeurIPS Taiji Suzuki, Atsushi Nitanda
2021	A*	`conf`	Differentiable Multiple Shooting Layers. NeurIPS Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama
2021	J	`jnl`	Differentiable Multiple Shooting Layers. CoRR Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama
2021	A	`conf`	Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features. AISTATS Shingo Yashima, Atsushi Nitanda, Taiji Suzuki
2021	J	`jnl`	Goodness-of-fit Test on the Number of Biclusters in Relational Data Matrix. CoRR Chihiro Watanabe, Taiji Suzuki
2021	J	`jnl`	Goodness-of-fit test for latent block models. Comput. Stat. Data Anal. Chihiro Watanabe, Taiji Suzuki
2021	A	`conf`	Gradient Descent in RKHS with Importance Labeling. AISTATS Tomoya Murata, Taiji Suzuki
2021	J	`jnl`	Neural Network Module Decomposition and Recomposition. CoRR Hiroaki Kingetsu, Kenichi Kobayashi, Taiji Suzuki
2021	A*	`conf`	On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting. ICML Shunta Akiyama, Taiji Suzuki
2021	J	`jnl`	On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting. CoRR Shunta Akiyama, Taiji Suzuki
2021	A*	`conf`	Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime. ICLR Atsushi Nitanda, Taiji Suzuki
2021	A*	`conf`	Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis. NeurIPS Atsushi Nitanda, Denny Wu, Taiji Suzuki
2021	A*	`conf`	Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding. ICML Akira Nakagawa, Keizo Kato, Taiji Suzuki
2021	J	`jnl`	Sharp characterization of optimal minibatch size for stochastic finite sum convex optimization. Knowl. Inf. Syst. Atsushi Nitanda, Tomoya Murata, Taiji Suzuki
2021	A*	`conf`	When does preconditioning help or hurt generalization? ICLR Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
2020	J	`jnl`	A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model. Comput. Stat. Data Anal. Shaogao Lv, Zengyan Fan, Heng Lian, Taiji Suzuki, Kenji Fukumizu
2020	J	`jnl`	Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods. CoRR Taiji Suzuki, Shunta Akiyama
2020	A*	`conf`	Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network. ICLR Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura
2020	J	`jnl`	Dimension-free convergence rates for gradient Langevin dynamics in RKHS. CoRR Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki
2020	A	`conf`	Domain Adaptation Regularization for Spectral Pruning. BMVC Laurent Dillard, Yosuke Shinya, Taiji Suzuki
2020	J	`jnl`	Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space. CoRR Kazuma Tsuji, Taiji Suzuki
2020	A	`conf`	Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees. AISTATS Atsushi Nitanda, Taiji Suzuki
2020	A*	`conf`	Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics. NeurIPS Taiji Suzuki
2020	J	`jnl`	Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics. CoRR Taiji Suzuki
2020	A*	`conf`	Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint. ICLR Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang
2020	J	`jnl`	Gradient Descent in RKHS with Importance Labeling. CoRR Tomoya Murata, Taiji Suzuki
2020	A*	`conf`	Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. ICLR Kenta Oono, Taiji Suzuki
2020	J	`jnl`	Independently Interpretable Lasso for Generalized Linear Models. Neural Comput. Masaaki Takada, Taiji Suzuki, Hironori Fujisawa
2020	J	`jnl`	Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error. CoRR Yusuke Hayashi, Taiji Suzuki
2020	J	`jnl`	Neural Architecture Search Using Stable Rank of Convolutional Layers. CoRR Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki
2020	J	`jnl`	On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces. Neural Networks Satoshi Hayakawa, Taiji Suzuki
2020	J	`jnl`	Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime. CoRR Atsushi Nitanda, Taiji Suzuki
2020	A*	`conf`	Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks. NeurIPS Kenta Oono, Taiji Suzuki
2020	J	`jnl`	Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks. CoRR Kenta Oono, Taiji Suzuki
2020	J	`jnl`	Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis. CoRR Atsushi Nitanda, Denny Wu, Taiji Suzuki
2020	J	`jnl`	Selective Inference for Latent Block Models. CoRR Chihiro Watanabe, Taiji Suzuki
2020	A*	`conf`	Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error. IJCAI Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura
2020	A	`conf`	Understanding Generalization in Deep Learning via Tensor Methods. AISTATS Jingling Li, Yanchao Sun, Jiahao Su, Taiji Suzuki, Furong Huang
2020	J	`jnl`	Understanding Generalization in Deep Learning via Tensor Methods. CoRR Jingling Li, Yanchao Sun, Jiahao Su, Taiji Suzuki, Furong Huang
2020	J	`jnl`	When Does Preconditioning Help or Hurt Generalization? CoRR Shun-ichi Amari, Jimmy Ba, Roger B. Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
2019	J	`jnl`	Accelerated Sparsified SGD with Error Feedback. CoRR Tomoya Murata, Taiji Suzuki
2019	—	`conf`	Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality. ICLR (Poster) Taiji Suzuki
2019	J	`jnl`	Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks. CoRR Kenta Oono, Taiji Suzuki
2019	A*	`conf`	Approximation and non-parametric estimation of ResNet-type convolutional neural networks. ICML Kenta Oono, Taiji Suzuki
2019	J	`jnl`	Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network. CoRR Taiji Suzuki
2019	—	`conf`	Cross-Domain Recommendation via Deep Domain Adaptation. ECIR (2) Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, Taiji Suzuki
2019	J	`jnl`	Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space. CoRR Taiji Suzuki, Atsushi Nitanda
2019	J	`jnl`	Domain Adaptation Regularization for Spectral Pruning. CoRR Laurent Dillard, Yosuke Shinya, Taiji Suzuki
2019	J	`jnl`	Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features. CoRR Shingo Yashima, Atsushi Nitanda, Taiji Suzuki
2019	J	`jnl`	Goodness-of-fit Test for Latent Block Models. CoRR Chihiro Watanabe, Taiji Suzuki
2019	J	`jnl`	Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD. CoRR Kosuke Haruki, Taiji Suzuki, Yohei Hamakawa, Takeshi Toda, Ryuji Sakai, Masahiro Ozawa, Mitsuhiro Kimura
2019	J	`jnl`	On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective. CoRR Kenta Oono, Taiji Suzuki
2019	J	`jnl`	On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces. CoRR Satoshi Hayakawa, Taiji Suzuki
2019	C	`ed.`	Proceedings of The 11th Asian Conference on Machine Learning, ACML 2019, 17-19 November 2019, Nagoya, Japan. ACML Wee Sun Lee, Taiji Suzuki
2019	J	`jnl`	Refined Generalization Analysis of Gradient Descent for Over-parameterized Two-layer Neural Networks with Smooth Activations on Classification Problems. CoRR Atsushi Nitanda, Taiji Suzuki
2019	J	`jnl`	Scalable Deep Neural Networks via Low-Rank Matrix Factorization. CoRR Atsushi Yaguchi, Taiji Suzuki, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa
2019	A*	`conf`	Sharp Characterization of Optimal Minibatch Size for Stochastic Finite Sum Convex Optimization. ICDM Atsushi Nitanda, Tomoya Murata, Taiji Suzuki
2019	A	`conf`	Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors. AISTATS Atsushi Nitanda, Taiji Suzuki
2019	—	`conf`	Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum. ICCV Workshops Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki
2019	J	`jnl`	Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum. CoRR Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki
2018	C	`conf`	Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks. ICMLA Atsushi Yaguchi, Taiji Suzuki, Wataru Asano, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa
2018	J	`jnl`	Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks. CoRR Atsushi Yaguchi, Taiji Suzuki, Wataru Asano, Shuhei Nitta, Yukinobu Sakata, Akiyuki Tanizawa
2018	J	`jnl`	Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality. CoRR Taiji Suzuki
2018	J	`jnl`	Cross-domain Recommendation via Deep Domain Adaptation. CoRR Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, Taiji Suzuki
2018	A	`conf`	Fast generalization error bound of deep learning from a kernel perspective. AISTATS Taiji Suzuki
2018	A*	`conf`	Functional Gradient Boosting based on Residual Network Perception. ICML Atsushi Nitanda, Taiji Suzuki
2018	J	`jnl`	Functional Gradient Boosting based on Residual Network Perception. CoRR Atsushi Nitanda, Taiji Suzuki
2018	J	`jnl`	Generalized ridge estimator and model selection criteria in multivariate linear regression. J. Multivar. Anal. Yuichi Mori, Taiji Suzuki
2018	A	`conf`	Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models. AISTATS Atsushi Nitanda, Taiji Suzuki
2018	J	`jnl`	Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models. CoRR Atsushi Nitanda, Taiji Suzuki
2018	A	`conf`	Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables. AISTATS Masaaki Takada, Taiji Suzuki, Hironori Fujisawa
2018	A*	`conf`	Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation. NeurIPS Tomoya Murata, Taiji Suzuki
2018	J	`jnl`	Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation. CoRR Tomoya Murata, Taiji Suzuki
2018	—	`conf`	Short-term local weather forecast using dense weather station by deep neural network. IEEE BigData Kazuo Yonekura, Hitoshi Hattori, Taiji Suzuki
2018	J	`jnl`	Spectral-Pruning: Compressing deep neural network via spectral analysis. CoRR Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura
2018	J	`jnl`	Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errors. CoRR Atsushi Nitanda, Taiji Suzuki
2017	—	`conf`	Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization. NIPS Tomoya Murata, Taiji Suzuki
2017	J	`jnl`	Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization. CoRR Tomoya Murata, Taiji Suzuki
2017	J	`jnl`	Fast learning rate of deep learning via a kernel perspective. CoRR Taiji Suzuki
2017	A	`conf`	Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann Machines. AISTATS Atsushi Nitanda, Taiji Suzuki
2017	J	`jnl`	Stochastic Particle Gradient Descent for Infinite Ensembles. CoRR Atsushi Nitanda, Taiji Suzuki
2017	—	`conf`	Trimmed Density Ratio Estimation. NIPS Song Liu, Akiko Takeda, Taiji Suzuki, Kenji Fukumizu
2016	A*	`conf`	Gaussian process nonparametric tensor estimator and its minimax optimality. ICML Heishiro Kanagawa, Taiji Suzuki, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami
2016	—	`conf`	Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning. NIPS Taiji Suzuki, Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami
2016	J	`jnl`	Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems. CoRR Tomoya Murata, Taiji Suzuki
2016	A*	`conf`	Structure Learning of Partitioned Markov Networks. ICML Song Liu, Taiji Suzuki, Masashi Sugiyama, Kenji Fukumizu
2016	J	`jnl`	System identification and parameter estimation in mathematical medicine: examples demonstrated for prostate cancer. Quant. Biol. Yoshito Hirata, Kai Morino, Taiji Suzuki, Qian Guo, Hiroshi Fukuhara, Kazuyuki Aihara
2015	A	`conf`	A Consistent Method for Graph Based Anomaly Localization. AISTATS Satoshi Hara, Tetsuro Morimura, Toshihiro Takahashi, Hiroki Yanagisawa, Taiji Suzuki
2015	A*	`conf`	Convergence rate of Bayesian tensor estimator and its minimax optimality. ICML Taiji Suzuki
2015	A*	`conf`	Support Consistency of Direct Sparse-Change Learning in Markov Networks. AAAI Song Liu, Taiji Suzuki, Masashi Sugiyama
2014	J	`jnl`	Convergence rate of Bayesian tensor estimator: Optimal rate without restricted strong convexity. CoRR Taiji Suzuki
2014	J	`jnl`	Direct Learning of Sparse Changes in Markov Networks by Density Ratio Estimation. Neural Comput. Song Liu, John A. Quinn, Michael U. Gutmann, Taiji Suzuki, Masashi Sugiyama
2014	A*	`conf`	Stochastic Dual Coordinate Ascent with Alternating Direction Method of Multipliers. ICML Taiji Suzuki
2013	J	`jnl`	Computational complexity of kernel-based density-ratio estimation: a condition number analysis. Mach. Learn. Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama
2013	J	`jnl`	Conjugate relation between loss functions and uncertainty sets in classification problems. J. Mach. Learn. Res. Takafumi Kanamori, Akiko Takeda, Taiji Suzuki
2013	J	`jnl`	Convex Tensor Decomposition via Structured Schatten Norm Regularization CoRR Ryota Tomioka, Taiji Suzuki
2013	—	`conf`	Convex Tensor Decomposition via Structured Schatten Norm Regularization. NIPS Ryota Tomioka, Taiji Suzuki
2013	J	`jnl`	Density-Difference Estimation. Neural Comput. Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, Ichiro Takeuchi
2013	J	`jnl`	Direct Divergence Approximation between Probability Distributions and Its Applications in Machine Learning. J. Comput. Sci. Eng. Masashi Sugiyama, Song Liu, Marthinus Christoffel du Plessis, Masao Yamanaka, Makoto Yamada, Taiji Suzuki, Takafumi Kanamori
2013	—	`conf`	Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method. ICML (1) Taiji Suzuki
2013	J	`jnl`	Improvement of multiple kernel learning using adaptively weighted regularization. JSIAM Lett. Taiji Suzuki
2013	J	`jnl`	Relative Density-Ratio Estimation for Robust Distribution Comparison. Neural Comput. Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Masashi Sugiyama
2013	J	`jnl`	Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation. Neural Comput. Taiji Suzuki, Masashi Sugiyama
2012	J	`jnl`	A Conjugate Property between Loss Functions and Uncertainty Sets in Classification Problems CoRR Takafumi Kanamori, Akiko Takeda, Taiji Suzuki
2012	A*	`conf`	A Conjugate Property between Loss Functions and Uncertainty Sets in Classification Problems. COLT Takafumi Kanamori, Akiko Takeda, Taiji Suzuki
2012	—	`book`	Density Ratio Estimation in Machine Learning. Masashi Sugiyama, Taiji Suzuki, Takafumi Kanamori
2012	J	`jnl`	Density-Difference Estimation CoRR Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, Ichiro Takeuchi
2012	—	`conf`	Density-Difference Estimation. NIPS Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, Ichiro Takeuchi
2012	A	`conf`	Fast Learning Rate of Multiple Kernel Learning: Trade-Off between Sparsity and Smoothness. AISTATS Taiji Suzuki, Masashi Sugiyama
2012	A*	`conf`	PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model. COLT Taiji Suzuki
2012	J	`jnl`	Statistical analysis of kernel-based least-squares density-ratio estimation. Mach. Learn. Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama
2012	J	`jnl`	f-Divergence Estimation and Two-Sample Homogeneity Test Under Semiparametric Density-Ratio Models. IEEE Trans. Inf. Theory Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama
2011	J	`jnl`	Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search. Neural Networks Masashi Sugiyama, Makoto Yamada, Paul von Bünau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe
2011	J	`jnl`	Least-Squares Independence Test. IEICE Trans. Inf. Syst. Masashi Sugiyama, Taiji Suzuki
2011	J	`jnl`	Least-Squares Independent Component Analysis. Neural Comput. Taiji Suzuki, Masashi Sugiyama
2011	J	`jnl`	Least-squares two-sample test. Neural Networks Masashi Sugiyama, Taiji Suzuki, Yuta Itoh, Takafumi Kanamori, Manabu Kimura
2011	—	`conf`	Relative Density-Ratio Estimation for Robust Distribution Comparison. NIPS Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Masashi Sugiyama
2011	J	`jnl`	SpicyMKL: a fast algorithm for Multiple Kernel Learning with thousands of kernels. Mach. Learn. Taiji Suzuki, Ryota Tomioka
2011	—	`conf`	Statistical Performance of Convex Tensor Decomposition. NIPS Ryota Tomioka, Taiji Suzuki, Kohei Hayashi, Hisashi Kashima
2011	J	`jnl`	Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparsity Regularized Estimation. J. Mach. Learn. Res. Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama
2011	—	`conf`	Unifying Framework for Fast Learning Rate of Non-Sparse Multiple Kernel Learning. NIPS Taiji Suzuki
2010	A*	`conf`	A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices. ICML Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama, Hisashi Kashima
2010	A	`conf`	Conditional Density Estimation via Least-Squares Density Ratio Estimation. AISTATS Masashi Sugiyama, Ichiro Takeuchi, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Daisuke Okanohara
2010	A	`conf`	Direct Density Ratio Estimation with Dimensionality Reduction. SDM Masashi Sugiyama, Satoshi Hara, Paul von Bünau, Taiji Suzuki, Takafumi Kanamori, Motoaki Kawanabe
2010	J	`jnl`	Least-Squares Conditional Density Estimation. IEICE Trans. Inf. Syst. Masashi Sugiyama, Ichiro Takeuchi, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Daisuke Okanohara
2010	J	`jnl`	Regularization Strategies and Empirical Bayesian Learning for MKL. CoRR Ryota Tomioka, Taiji Suzuki
2010	A	`conf`	Sufficient Dimension Reduction via Squared-loss Mutual Information Estimation. AISTATS Taiji Suzuki, Masashi Sugiyama
2010	J	`jnl`	Theoretical Analysis of Density Ratio Estimation. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Takafumi Kanamori, Taiji Suzuki, Masashi Sugiyama
2009	J	`jnl`	A Density-ratio Framework for Statistical Data Processing. Inf. Media Technol. Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Shohei Hido, Jun Sese, Ichiro Takeuchi, Liwei Wang
2009	J	`jnl`	A Density-ratio Framework for Statistical Data Processing. IPSJ Trans. Comput. Vis. Appl. Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Shohei Hido, Jun Sese, Ichiro Takeuchi, Liwei Wang
2009	—	`conf`	Estimating Squared-Loss Mutual Information for Independent Component Analysis. ICA Taiji Suzuki, Masashi Sugiyama
2009	B	`conf`	Mutual information approximation via maximum likelihood estimation of density ratio. ISIT Taiji Suzuki, Masashi Sugiyama, Toshiyuki Tanaka
2009	J	`jnl`	Mutual information estimation reveals global associations between stimuli and biological processes. BMC Bioinform. Taiji Suzuki, Masashi Sugiyama, Takafumi Kanamori, Jun Sese
2009	J	`jnl`	Super-Linear Convergence of Dual Augmented-Lagrangian Algorithm for Sparsity Regularized Estimation. CoRR Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama
2008	—	`conf`	Approximating Mutual Information by Maximum Likelihood Density Ratio Estimation. FSDM Taiji Suzuki, Masashi Sugiyama, Jun Sese, Takafumi Kanamori
2005	C	`conf`	Learning to estimate user interest utilizing the variational Bayes estimator. ISDA Taiji Suzuki, Takamasa Koshizen, Kazuyuki Aihara, Hiroshi Tsujino