Masaaki Imaizumi

According to our database, Masaaki Imaizumi authored at least 73 papers between 1997 and 2026.

Collaborative distances:

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

2026

Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables.

Masaaki Imaizumi, Masanori Koyama, Noboru Isobe, Kohei Hayashi

CoRR, May, 2026

Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality.

Shu Tamano, Masaaki Imaizumi

CoRR, May, 2026

Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers.

Noboru Isobe, Daisuke Inoue, Masaaki Imaizumi

CoRR, May, 2026

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers.

Mana Sakai, Masaaki Imaizumi

CoRR, May, 2026

CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency.

Hirofumi Ota, Naoto Iwase, Yuki Ichihara, Junpei Komiyama, Masaaki Imaizumi

CoRR, May, 2026

Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent.

Shota Imai, Sota Nishiyama, Masaaki Imaizumi

CoRR, February, 2026

High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory.

Sota Nishiyama, Masaaki Imaizumi

CoRR, February, 2026

Neuron Block Dynamics for XOR Classification with Zero-Margin.

Guillaume Braun, Masaaki Imaizumi

CoRR, February, 2026

Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval.

Guillaume Braun, Han Bao, Wei Huang, Masaaki Imaizumi

CoRR, January, 2026

Finite-Sample Inference for Sparsely Permuted Linear Regression.

Hirofumi Ota, Masaaki Imaizumi

CoRR, January, 2026

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion.

Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji

Trans. Mach. Learn. Res., 2026

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings.

Tomomasa Hara, Hiroto Kurita, Masaaki Imaizumi, Kentaro Inui, Sho Yokoi

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry.

Naoki Yoshida, Isao Ishikawa, Masaaki Imaizumi

CoRR, December, 2025

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data.

Guillaume Braun, Bruno Loureiro, Ha Quang Minh, Masaaki Imaizumi

CoRR, November, 2025

Wasserstein k-Centers Clustering for Distributional Data.

Ryo Okano, Masaaki Imaizumi

Stat. Comput., October, 2025

SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator.

Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya, Masaaki Imaizumi, Naoki Murata, Bac Nguyen, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuki Mitsufuji

CoRR, October, 2025

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory.

Sota Nishiyama, Masaaki Imaizumi

CoRR, October, 2025

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning.

Baiyuan Chen, Shinji Ito, Masaaki Imaizumi

CoRR, August, 2025

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs.

Mana Sakai, Ryo Karakida, Masaaki Imaizumi

CoRR, June, 2025

High-dimensional Nonparametric Contextual Bandit Problem.

Shogo Iwazaki, Junpei Komiyama, Masaaki Imaizumi

CoRR, May, 2025

Precise gradient descent training dynamics for finite-width multi-layer neural networks.

Qiyang Han, Masaaki Imaizumi

CoRR, May, 2025

Distillation of Discrete Diffusion through Dimensional Correlations.

Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji

Dataset, April, 2025

Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size.

Naoki Takeshita, Masaaki Imaizumi

CoRR, February, 2025

Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution.

Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi

Trans. Mach. Learn. Res., 2025

Landscape computations for the edge of chaos in nonlinear dynamical systems.

Motoki Nakata, Masaaki Imaizumi

JSIAM Lett., 2025

Distillation of Discrete Diffusion through Dimensional Correlations.

Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Encode-Decoder-based GAN for Estimating Counterfactual Outcomes under Sequential Selection Bias and Combinatorial Explosion.

Yoshiyuki Norimatsu, Masaaki Imaizumi

Proceedings of the Causal Learning and Reasoning, Lausanne, Switzerland, 7-9 May 2025., 2025

Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent.

Guillaume Braun, Minh Ha Quang, Masaaki Imaizumi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer.

Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

Dataset, April, 2024

Distribution-on-distribution regression with Wasserstein metric: Multivariate Gaussian case.

Ryo Okano, Masaaki Imaizumi

J. Multivar. Anal., 2024

Federated Learning with Relative Fairness.

Shogo Nakakita, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki, Masaaki Imaizumi

CoRR, 2024

Automatic Domain Adaptation by Transformers in In-Context Learning.

Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi

CoRR, 2024

Effect of Weight Quantization on Learning Models by Typical Case Analysis.

Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi

Proceedings of the IEEE International Symposium on Information Theory, 2024

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer.

Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer.

Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

Dataset, July, 2023

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer.

Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

Dataset, July, 2023

On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization.

Masaaki Imaizumi, Johannes Schmidt-Hieber

IEEE Trans. Inf. Theory, February, 2023

CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression.

Masahiro Kato, Masaaki Imaizumi

CoRR, 2023

Synthetic Control Methods by Density Matching under Implicit Endogeneity.

Masahiro Kato, Akari Ohda, Masaaki Imaizumi, Kenichiro McAlinn

CoRR, 2023

Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Training.

Masaaki Imaizumi

CoRR, 2023

Asymptotically Minimax Optimal Fixed-Budget Best Arm Identification for Expected Simple Regret Minimization.

Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa

CoRR, 2023

Adversarially Slicing Generative Networks: Discriminator Slices Feature for One-Dimensional Optimal Transport.

Yuhta Takida, Masaaki Imaizumi, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

CoRR, 2023

High-dimensional Contextual Bandit Problem without Sparsity.

Junpei Komiyama, Masaaki Imaizumi

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

Unified Perspective on Probability Divergence via the Density-Ratio Likelihood: Bridging KL-Divergence and Integral Probability Metrics.

Masahiro Kato, Masaaki Imaizumi, Kentaro Minami

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Hypothesis Test and Confidence Analysis With Wasserstein Distance on General Dimension.

Masaaki Imaizumi, Hirofumi Ota, Takuo Hamaguchi

Neural Comput., 2022

Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces.

Masaaki Imaizumi, Kenji Fukumizu

J. Mach. Learn. Res., 2022

Semiparametric Best Arm Identification with Contextual Information.

Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa

CoRR, 2022

Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression.

Masahiro Kato, Masaaki Imaizumi

CoRR, 2022

Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics.

Masahiro Kato, Masaaki Imaizumi, Kentaro Minami

CoRR, 2022

Optimal Fixed-Budget Best Arm Identification using the Augmented Inverse Probability Weighting Estimator in Two-Armed Gaussian Bandits with Unknown Variances.

Masahiro Kato, Kaito Ariu, Masaaki Imaizumi, Masatoshi Uehara, Masahiro Nomura, Chao Qin

CoRR, 2022

Learning Causal Models from Conditional Moment Restrictions by Importance Weighting.

Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Shota Yasui, Haruo Kakehi

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Quasi-potential theory for escape problem: Quantitative sharpness effect on SGD's escape from local minima.

Hikaru Ibayashi, Masaaki Imaizumi

CoRR, 2021

Minimum sharpness: Scale-invariant parameter-robustness of neural networks.

Hikaru Ibayashi, Takuo Hamaguchi, Masaaki Imaizumi

CoRR, 2021

Instrument Space Selection for Kernel Maximum Moment Restriction.

Rui Zhang, Krikamol Muandet, Bernhard Schölkopf, Masaaki Imaizumi

CoRR, 2021

Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks.

Ryumei Nakada, Masaaki Imaizumi

CoRR, 2021

Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach.

Manohar Kaul, Masaaki Imaizumi

CoRR, 2021

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency.

Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang, Nathan Kallus, Wen Sun, Tengyang Xie

CoRR, 2021

Improved generalization bounds of group invariant / equivariant deep networks via quotient feature spaces.

Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Fréchet Kernel for Trajectory Data Analysis.

Koh Takeuchi, Masaaki Imaizumi, Shunsuke Kanda, Yasuo Tabei, Keisuke Fujii, Ken Yoda, Masakazu Ishihata, Takuya Maekawa

Proceedings of the SIGSPATIAL '21: 29th International Conference on Advances in Geographic Information Systems, 2021

2020

Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality.

Ryumei Nakada, Masaaki Imaizumi

J. Mach. Learn. Res., 2020

Advantage of Deep Neural Networks for Estimating Functions with Singularity on Curves.

Masaaki Imaizumi, Kenji Fukumizu

CoRR, 2020

Maximum Moment Restriction for Instrumental Variable Regression.

Rui Zhang, Masaaki Imaizumi, Bernhard Schölkopf, Krikamol Muandet

CoRR, 2020

On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis.

Kohei Hayashi, Masaaki Imaizumi, Yuichi Yoshida

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

2019

Improved Generalization Bound of Permutation Invariant Deep Neural Networks.

Akiyoshi Sannai, Masaaki Imaizumi

CoRR, 2019

Adaptive Approximation and Estimation of Deep Neural Network to Intrinsic Dimensionality.

Ryumei Nakada, Masaaki Imaizumi

CoRR, 2019

Deep Neural Networks Learn Non-Smooth Functions Effectively.

Masaaki Imaizumi, Kenji Fukumizu

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

2018

PCA-based estimation for functional linear regression with functional responses.

Masaaki Imaizumi, Kengo Kato

J. Multivar. Anal., 2018

Statistically Efficient Estimation for Non-Smooth Probability Densities.

Masaaki Imaizumi, Takanori Maehara, Yuichi Yoshida

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

2017

On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm.

Masaaki Imaizumi, Takanori Maehara, Kohei Hayashi

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

Factorized Asymptotic Bayesian Policy Search for POMDPs.

Masaaki Imaizumi, Ryohei Fujimaki

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Tensor Decomposition with Smoothness.

Masaaki Imaizumi, Kohei Hayashi

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

Doubly Decomposing Nonparametric Tensor Regression.

Masaaki Imaizumi, Kohei Hayashi

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

1997

Resolutionable cellular neural networks.

Mamoru Tanaka, Kenya Jin'no, Jun'ichi Miyata, Masaaki Imaizumi, Toshiaki Shingu, Hiroshi Inoue

Proceedings of International Conference on Neural Networks (ICNN'97), 1997