Masaaki Imaizumi

71 papers A* 7A 6B 1Journal 53Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion. Trans. Mach. Learn. Res. Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2026	J	`jnl`	Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent. CoRR Shota Imai, Sota Nishiyama, Masaaki Imaizumi
2026	J	`jnl`	Finite-Sample Inference for Sparsely Permuted Linear Regression. CoRR Hirofumi Ota, Masaaki Imaizumi
2026	J	`jnl`	High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory. CoRR Sota Nishiyama, Masaaki Imaizumi
2026	J	`jnl`	Neuron Block Dynamics for XOR Classification with Zero-Margin. CoRR Guillaume Braun, Masaaki Imaizumi
2026	J	`jnl`	Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval. CoRR Guillaume Braun, Han Bao, Wei Huang, Masaaki Imaizumi
2025	J	`jnl`	Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size. CoRR Naoki Takeshita, Masaaki Imaizumi
2025	J	`jnl`	Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion. CoRR Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2025	A*	`conf`	Distillation of Discrete Diffusion through Dimensional Correlations. ICML Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2025	J	`jnl`	Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution. Trans. Mach. Learn. Res. Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi
2025	—	`conf`	Encode-Decoder-based GAN for Estimating Counterfactual Outcomes under Sequential Selection Bias and Combinatorial Explosion. CLeaR Yoshiyuki Norimatsu, Masaaki Imaizumi
2025	J	`jnl`	Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data. CoRR Guillaume Braun, Bruno Loureiro, Ha Quang Minh, Masaaki Imaizumi
2025	J	`jnl`	High-dimensional Nonparametric Contextual Bandit Problem. CoRR Shogo Iwazaki, Junpei Komiyama, Masaaki Imaizumi
2025	J	`jnl`	Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs. CoRR Mana Sakai, Ryo Karakida, Masaaki Imaizumi
2025	J	`jnl`	Landscape computations for the edge of chaos in nonlinear dynamical systems. JSIAM Lett. Motoki Nakata, Masaaki Imaizumi
2025	A	`conf`	Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent. AISTATS Guillaume Braun, Minh Ha Quang, Masaaki Imaizumi
2025	J	`jnl`	Learning a Single Index Model from Anisotropic Data with vanilla Stochastic Gradient Descent. CoRR Guillaume Braun, Minh Ha Quang, Masaaki Imaizumi
2025	J	`jnl`	Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning. CoRR Baiyuan Chen, Shinji Ito, Masaaki Imaizumi
2025	J	`jnl`	Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory. CoRR Sota Nishiyama, Masaaki Imaizumi
2025	J	`jnl`	Precise gradient descent training dynamics for finite-width multi-layer neural networks. CoRR Qiyang Han, Masaaki Imaizumi
2025	J	`jnl`	SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator. CoRR Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya, Masaaki Imaizumi, Naoki Murata, Bac Nguyen, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuki Mitsufuji
2025	J	`jnl`	Wasserstein k-Centers Clustering for Distributional Data. Stat. Comput. Ryo Okano, Masaaki Imaizumi
2025	J	`jnl`	Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry. CoRR Naoki Yoshida, Isao Ishikawa, Masaaki Imaizumi
2024	J	`jnl`	Automatic Domain Adaptation by Transformers in In-Context Learning. CoRR Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi
2024	J	`jnl`	Distillation of Discrete Diffusion through Dimensional Correlations. CoRR Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2024	J	`jnl`	Distribution-on-distribution regression with Wasserstein metric: Multivariate Gaussian case. J. Multivar. Anal. Ryo Okano, Masaaki Imaizumi
2024	J	`jnl`	Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution. CoRR Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi
2024	B	`conf`	Effect of Weight Quantization on Learning Models by Typical Case Analysis. ISIT Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi
2024	J	`jnl`	Effect of Weight Quantization on Learning Models by Typical Case Analysis. CoRR Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi
2024	J	`jnl`	Federated Learning with Relative Fairness. CoRR Shogo Nakakita, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki, Masaaki Imaizumi
2024	A*	`conf`	SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer. ICLR Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji
2023	J	`jnl`	Adversarially Slicing Generative Networks: Discriminator Slices Feature for One-Dimensional Optimal Transport. CoRR Yuhta Takida, Masaaki Imaizumi, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji
2023	J	`jnl`	Asymptotically Minimax Optimal Fixed-Budget Best Arm Identification for Expected Simple Regret Minimization. CoRR Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa
2023	J	`jnl`	CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression. CoRR Masahiro Kato, Masaaki Imaizumi
2023	A*	`conf`	High-dimensional Contextual Bandit Problem without Sparsity. NeurIPS Junpei Komiyama, Masaaki Imaizumi
2023	J	`jnl`	High-dimensional Contextual Bandit Problem without Sparsity. CoRR Junpei Komiyama, Masaaki Imaizumi
2023	J	`jnl`	On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE Trans. Inf. Theory Masaaki Imaizumi, Johannes Schmidt-Hieber
2023	J	`jnl`	Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Training. CoRR Masaaki Imaizumi
2023	J	`jnl`	Synthetic Control Methods by Density Matching under Implicit Endogeneity. CoRR Masahiro Kato, Akari Ohda, Masaaki Imaizumi, Kenichiro McAlinn
2023	A	`conf`	Unified Perspective on Probability Divergence via the Density-Ratio Likelihood: Bridging KL-Divergence and Integral Probability Metrics. AISTATS Masahiro Kato, Masaaki Imaizumi, Kentaro Minami
2022	J	`jnl`	Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces. J. Mach. Learn. Res. Masaaki Imaizumi, Kenji Fukumizu
2022	J	`jnl`	Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression. CoRR Masahiro Kato, Masaaki Imaizumi
2022	J	`jnl`	Hypothesis Test and Confidence Analysis With Wasserstein Distance on General Dimension. Neural Comput. Masaaki Imaizumi, Hirofumi Ota, Takuo Hamaguchi
2022	A*	`conf`	Learning Causal Models from Conditional Moment Restrictions by Importance Weighting. ICLR Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Shota Yasui, Haruo Kakehi
2022	J	`jnl`	On generalization bounds for deep networks based on loss surface implicit regularization. CoRR Masaaki Imaizumi, Johannes Schmidt-Hieber
2022	J	`jnl`	Optimal Fixed-Budget Best Arm Identification using the Augmented Inverse Probability Weighting Estimator in Two-Armed Gaussian Bandits with Unknown Variances. CoRR Masahiro Kato, Kaito Ariu, Masaaki Imaizumi, Masatoshi Uehara, Masahiro Nomura, Chao Qin
2022	J	`jnl`	Semiparametric Best Arm Identification with Contextual Information. CoRR Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa
2022	J	`jnl`	Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics. CoRR Masahiro Kato, Masaaki Imaizumi, Kentaro Minami
2021	J	`jnl`	Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks. CoRR Ryumei Nakada, Masaaki Imaizumi
2021	J	`jnl`	Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency. CoRR Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang, Nathan Kallus, Wen Sun, Tengyang Xie
2021	—	`conf`	Fréchet Kernel for Trajectory Data Analysis. SIGSPATIAL/GIS Koh Takeuchi, Masaaki Imaizumi, Shunsuke Kanda, Yasuo Tabei, Keisuke Fujii, Ken Yoda, Masakazu Ishihata, Takuya Maekawa
2021	A	`conf`	Improved generalization bounds of group invariant / equivariant deep networks via quotient feature spaces. UAI Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano
2021	J	`jnl`	Instrument Space Selection for Kernel Maximum Moment Restriction. CoRR Rui Zhang, Krikamol Muandet, Bernhard Schölkopf, Masaaki Imaizumi
2021	J	`jnl`	Minimum sharpness: Scale-invariant parameter-robustness of neural networks. CoRR Hikaru Ibayashi, Takuo Hamaguchi, Masaaki Imaizumi
2021	J	`jnl`	Quasi-potential theory for escape problem: Quantitative sharpness effect on SGD's escape from local minima. CoRR Hikaru Ibayashi, Masaaki Imaizumi
2021	J	`jnl`	Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach. CoRR Manohar Kaul, Masaaki Imaizumi
2020	J	`jnl`	Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality. J. Mach. Learn. Res. Ryumei Nakada, Masaaki Imaizumi
2020	J	`jnl`	Advantage of Deep Neural Networks for Estimating Functions with Singularity on Curves. CoRR Masaaki Imaizumi, Kenji Fukumizu
2020	J	`jnl`	Maximum Moment Restriction for Instrumental Variable Regression. CoRR Rui Zhang, Masaaki Imaizumi, Bernhard Schölkopf, Krikamol Muandet
2020	A	`conf`	On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis. AISTATS Kohei Hayashi, Masaaki Imaizumi, Yuichi Yoshida
2019	J	`jnl`	Adaptive Approximation and Estimation of Deep Neural Network to Intrinsic Dimensionality. CoRR Ryumei Nakada, Masaaki Imaizumi
2019	A	`conf`	Deep Neural Networks Learn Non-Smooth Functions Effectively. AISTATS Masaaki Imaizumi, Kenji Fukumizu
2019	J	`jnl`	Improved Generalization Bound of Permutation Invariant Deep Neural Networks. CoRR Akiyoshi Sannai, Masaaki Imaizumi
2019	J	`jnl`	On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis. CoRR Kohei Hayashi, Masaaki Imaizumi, Yuichi Yoshida
2018	J	`jnl`	PCA-based estimation for functional linear regression with functional responses. J. Multivar. Anal. Masaaki Imaizumi, Kengo Kato
2018	A	`conf`	Statistically Efficient Estimation for Non-Smooth Probability Densities. AISTATS Masaaki Imaizumi, Takanori Maehara, Yuichi Yoshida
2017	A*	`conf`	Factorized Asymptotic Bayesian Policy Search for POMDPs. IJCAI Masaaki Imaizumi, Ryohei Fujimaki
2017	—	`conf`	On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm. NIPS Masaaki Imaizumi, Takanori Maehara, Kohei Hayashi
2017	A*	`conf`	Tensor Decomposition with Smoothness. ICML Masaaki Imaizumi, Kohei Hayashi
2016	A*	`conf`	Doubly Decomposing Nonparametric Tensor Regression. ICML Masaaki Imaizumi, Kohei Hayashi
1997	—	`conf`	Resolutionable cellular neural networks. ICNN Mamoru Tanaka, Kenya Jin'no, Jun'ichi Miyata, Masaaki Imaizumi, Toshiaki Shingu, Hiroshi Inoue