Shunta Akiyama

Shunta Akiyama

Publications

Preprint

  1. K. Oko, S. Akiyama, T. Murata, T. Suzuki: Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning. [arXiv]

  2. S. Sonoda, S. Akiyama, Y. Uezato: Exponential Sample Complexity Separation between Flat and Hierarchical Agentic Theorem Provers. [arXiv]

International Conference Paper (accepted)

  1. T. Suzuki, S. Akiyama: Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods. International Conference on Learning Representations 2021. (selected as splotlight). [arXiv]

  2. S. Akiyama, T. Suzuki: On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting. International Conference on Machine Learning 2021. [arXiv]

  3. K. Oko, S. Akiyama, T. Murata and T. Suzuki: Reducing Communication in Nonconvex Federated Learning with a Novel Single-Loop Variance Reduction Method, OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), New Orleans, America, Dec. 2022.

  4. S. Akiyama, T. Suzuki: Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods. International Conference on Learning Representations 2023. [arXiv]

  5. K. Oko, S. Akiyama, T. Suzuki: Diffusion Models are Minimax Optimal Distribution Estimators. International Conference on Machine Learning 2023.[arXiv]

  6. S. Akiyama, K. Oko and T. Suzuki: Benign Overfitting of Two-Layer Neural Networks under Inputs with Intrinsic Dimensionality. HiLD 2023: 1st Workshop on High-dimensional Learning Dynamics (ICML 2023 workshop).

  7. K. Oko, S. Akiyama, D. Wu, T. Suzuki, T. Murata: SILVER: Single-loop variance reduction and application to federated learning. International Conference on Machine Learning 2024. [proceedings]

  8. H. Yanagisawa, S. Akiyama: Survival Analysis via Density Estimation. International Conference on Machine Learning 2025. [proceedings]

  9. S. Akiyama: Block Coordinate Descent for Neural Networks Provably Finds Global Minima. Annual Conference on Neural Information Processing Systems 2025. [arXiv]

  10. H. Yanagisawa, S. Akiyama: A Strictly Proper Scoring Rule and a Calibration Metric for Interval-Censored Data Analysis. International Conference on Machine Learning 2026.

  11. S. Sonoda, S. Akiyama, Y. Uezato: Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models. International Conference on Machine Learning 2026. [arXiv]

Journal Articles

  1. S. Akiyama*, M. Obara*, Y. Kawase: Optimal design of lottery with cumulative prospect theory. ACM Transactions on Economics and Computation (*equal contribution). [arXiv]