pith. sign in

Masaaki Imaizumi

Identifiers

  • name variant Masaaki Imaizumi 0.60 · backfill

Papers (60)

  1. Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables cs.LG · 2026 · author #1
  2. Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality math.ST · 2026 · author #2
  3. Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport math.ST · 2026 · author #3
  4. Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers cs.LG · 2026 · author #3
  5. Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers stat.ML · 2026 · author #2
  6. CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency stat.ML · 2026 · author #5
  7. Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings cs.CL · 2026 · author #3
  8. Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion cs.LG · 2025 · author #3
  9. High-dimensional Nonparametric Contextual Bandit Problem stat.ML · 2025 · author #3
  10. Precise gradient descent training dynamics for finite-width multi-layer neural networks cs.LG · 2025 · author #2
  11. Learning a Single Index Model from Anisotropic Data with vanilla Stochastic Gradient Descent stat.ML · 2025 · author #3
  12. Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size cs.LG · 2025 · author #2
  13. Federated Learning with Relative Fairness stat.ML · 2024 · author #4
  14. Distillation of Discrete Diffusion through Dimensional Correlations cs.LG · 2024 · author #3
  15. Wasserstein $k$-Centers Clustering for Distributional Data stat.ME · 2024 · author #2
  16. Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution stat.ML · 2024 · author #3
  17. Automatic Domain Adaptation by Transformers in In-Context Learning cs.LG · 2024 · author #3
  18. High-Dimensional Single-Index Models: Link Estimation and Marginal Inference math.ST · 2024 · author #3
  19. Effect of Weight Quantization on Learning Models by Typical Case Analysis stat.ML · 2024 · author #3
  20. CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression econ.EM · 2023 · author #2
  21. Uniform Confidence Band for Optimal Transport Map on One-Dimensional Data math.ST · 2023 · author #3
  22. Distribution-on-Distribution Regression with Wasserstein Metric: Multivariate Gaussian Case stat.ME · 2023 · author #2
  23. Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Training stat.ML · 2023 · author #1
  24. High-dimensional Contextual Bandit Problem without Sparsity stat.ML · 2023 · author #2
  25. Moment-Based Adjustments of Statistical Inference in High-Dimensional Generalized Linear Models math.ST · 2023 · author #3
  26. Bayesian Analysis for Over-parameterized Linear Model via Effective Spectra math.ST · 2023 · author #2
  27. Benign Overfitting of Non-Sparse High-Dimensional Linear Regression with Correlated Noise math.ST · 2023 · author #2
  28. Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds cs.LG · 2023 · author #2
  29. SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer cs.LG · 2023 · author #2
  30. Dimension-free Bounds for Sum of Dependent Matrices and Operators with Heavy-Tailed Distribution math.ST · 2022 · author #3
  31. Best Arm Identification with Contextual Information under a Small Gap cs.LG · 2022 · author #2
  32. Benign Overfitting in Time Series Linear Models with Over-Parameterization math.ST · 2022 · author #2
  33. Inference for Projection-Based Wasserstein Distances on Finite Spaces stat.ME · 2022 · author #2
  34. Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression econ.EM · 2022 · author #2
  35. Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics cs.LG · 2022 · author #2
  36. On generalization bounds for deep networks based on loss surface implicit regularization stat.ML · 2022 · author #1
  37. Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap stat.ML · 2022 · author #3
  38. Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression math.ST · 2021 · author #2
  39. Exponential escape efficiency of SGD from sharp minima in non-stationary regime cs.LG · 2021 · author #2
  40. Learning Causal Models from Conditional Moment Restrictions by Importance Weighting econ.EM · 2021 · author #2
  41. Minimum sharpness: Scale-invariant parameter-robustness of neural networks cs.LG · 2021 · author #3
  42. Instrument Space Selection for Kernel Maximum Moment Restriction cs.LG · 2021 · author #4
  43. Fast Convergence on Perfect Classification for Functional Data math.ST · 2021 · author #2
  44. Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks stat.ML · 2021 · author #2
  45. Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach cs.LG · 2021 · author #2
  46. Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency cs.LG · 2021 · author #2
  47. On Gaussian Approximation for M-Estimator math.ST · 2020 · author #1
  48. Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces stat.ML · 2020 · author #1
  49. Instrumental Variable Regression via Kernel Maximum Moment Loss cs.LG · 2020 · author #2
  50. Hypothesis Test and Confidence Analysis with Wasserstein Distance on General Dimension math.ST · 2019 · author #1
  51. Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces stat.ML · 2019 · author #2
  52. Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality stat.ML · 2019 · author #2
  53. On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis stat.ML · 2019 · author #2
  54. Deep Neural Networks Learn Non-Smooth Functions Effectively stat.ML · 2018 · author #1
  55. On Tensor Train Rank Minimization: Statistical Efficiency and Scalable Algorithm stat.ML · 2017 · author #1
  56. Consistent Nonparametric Different-Feature Selection via the Sparsest $k$-Subgraph Problem stat.ML · 2017 · author #4
  57. A simple method to construct confidence bands in functional linear regression math.ST · 2016 · author #1
  58. PCA-based estimation for functional linear regression with functional responses math.ST · 2016 · author #1
  59. Approximation method for discrete Markov decision models with a large state space stat.CO · 2015 · author #1
  60. Doubly Decomposing Nonparametric Tensor Regression stat.ML · 2015 · author #1

Mentions

  • 2406.16032 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2012.15678 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2306.11017 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2210.09756 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2407.08228 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2505.14102 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2410.08709 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2505.04898 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2305.15754 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2503.23642 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2204.08369 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2502.11467 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2411.01161 #4 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2405.16819 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2305.17731 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2404.17812 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2301.12811 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2307.09257 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2307.06137 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2401.17269 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2112.00213 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2310.16819 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2304.04037 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2302.02988 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2307.04042 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2010.07684 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2104.02978 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2209.07330 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2201.04469 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2201.04545 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2108.01312 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2102.02981 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2111.04004 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2202.05245 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1910.07773 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2202.05495 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2011.02256 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2201.13127 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2106.12612 #3 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1910.06552 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2106.03340 #4 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2103.00500 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 2102.03609 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1907.02177 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1901.09541 #2 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1802.04474 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1708.00132 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1707.09688 #4 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1612.07490 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1609.00286 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1506.06722 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1506.05967 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi
  • 1506.06722 #1 · backfill · confidence 0.70 Masaaki Imaizumi
  • 1506.05967 #1 · backfill · confidence 0.70 Masaaki Imaizumi
  • 2605.30229 #1 · arxiv_oai · confidence 0.70 Masaaki Imaizumi

Frequent Coauthors