顔写真

PHOTO

Futami Futoshi
二見　太
Futami Futoshi
二見　太
Graduate School of Engineering Science　Department of Systems Innovation，Associate Professor (Lecturer)

Research History 2

  1. 2022/10 - Present
    Osaka University　Graduate School of Engineering Science

  2. 2020/04 - 2022/10
    日本電信電話株式会社　コミュニケーション科学基礎研究所　研究員

Education 1

  1. 東京大学大学院　新領域創成科学研究科　複雑理工学専攻

    - 2020/03

Committee Memberships 1

  1. 電子情報通信学会　情報論的学習理論と機械学習研究専門委員会　Academic society

    2022/06 - Present

Professional Memberships 2

  1. 日本統計学会

  2. 電子通信情報学会

Research Areas 1

  1. Informatics / Statistical science /

Papers 16

  1. Epistemic Uncertainty and Excess Risk in Variational Inference.

    Futoshi Futami

    AISTATS　p. 568-576　2025　Research paper (international conference proceedings)

  2. On the Convergence of SVGD in KL divergence via Approximate gradient flow.

    Masahiro Fujisawa, Futoshi Futami

    Trans. Mach. Learn. Res.　Vol. 2025　2025　Research paper (scientific journal)

  3. Information-theoretic Generalization Analysis for Expected Calibration Error.

    Futoshi Futami, Masahiro Fujisawa

    NeurIPS　2024　Research paper (international conference proceedings)

  4. Information-theoretic Analysis of Bayesian Test Data Sensitivity.

    Futoshi Futami, Tomoharu Iwata

    AISTATS　p. 1099-1107　2024　Research paper (international conference proceedings)

    Publisher: PMLR

  5. Time-Independent Information-Theoretic Generalization Bounds for SGLD.

    Futoshi Futami, Masahiro Fujisawa

    NeurIPS　2023　Research paper (international conference proceedings)

  6. Predictive variational Bayesian inference as risk-seeking optimization.

    Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama

    International Conference on Artificial Intelligence and Statistics(AISTATS)　p. 5051-5083　2022/03　Research paper (international conference proceedings)

    Publisher: PMLR

  7. Excess risk analysis for epistemic uncertainty with application to variational inference.

    Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama

    CoRR　Vol. abs/2206.01606　2022　Research paper (scientific journal)

  8. Loss function based second-order Jensen inequality and its application to particle variational inference.

    Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama

    Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021(NeurIPS)　p. 6803-6815　2021/12　Research paper (international conference proceedings)

  9. Scalable gradient matching based on state space Gaussian Processes.

    Futoshi Futami

    Asian Conference on Machine Learning(ACML)　p. 769-784　2021/11　Research paper (international conference proceedings)

    Publisher: PMLR

  10. Skew-symmetrically perturbed gradient flow for convex optimization.

    Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Ikko Yamane

    Asian Conference on Machine Learning(ACML)　p. 721-736　2021/11　Research paper (international conference proceedings)

    Publisher: PMLR

  11. Accelerated Diffusion-Based Sampling by the Non-Reversible Dynamics with Skew-Symmetric Matrices.

    Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato

    Entropy　Vol. 23　No. 8　p. 993-993　2021/07　Research paper (scientific journal)

  12. Accelerating the diffusion-based ensemble sampling by non-reversible dynamics.

    Futoshi Futami, Issei Sato, Masashi Sugiyama

    Proceedings of the 37th International Conference on Machine Learning(ICML)　p. 3337-3347　2020/07　Research paper (international conference proceedings)

    Publisher: PMLR

  13. Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time.

    Hideaki Imamura, Nontawat Charoenphakdee, Futoshi Futami, Issei Sato, Junya Honda, Masashi Sugiyama

    CoRR　Vol. abs/2003.04691　2020　Research paper (scientific journal)

  14. Bayesian Posterior Approximation via Greedy Particle Optimization.

    Futoshi Futami, Zhenghang Cui, Issei Sato, Masashi Sugiyama

    The Thirty-Third AAAI Conference on Artificial Intelligence(AAAI)　p. 3606-3613　2019/01　Research paper (international conference proceedings)

    Publisher: AAAI Press

  15. Variational Inference based on Robust Divergences.

    Futoshi Futami, Issei Sato, Masashi Sugiyama

    International Conference on Artificial Intelligence and Statistics(AISTATS)　p. 813-822　2018/04　Research paper (international conference proceedings)

    Publisher: PMLR

  16. Expectation Propagation for t-Exponential Family Using q-Algebra.

    Futoshi Futami, Issei Sato, Masashi Sugiyama

    Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017(NIPS)　p. 2245-2254　2017/12　Research paper (international conference proceedings)