International Conference Papers (Peer Reviewed)
F. Futami* & M. Fujisawa*. Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables. To be appeared in Neural Information Processing Systems, 2025. (NeurIPS 2025) (https://arxiv.org/pdf/2505.19470) (* equal contribution)
M. Fujisawa* & F. Futami*. PAC-Bayes Analysis for Recalibration in Classification. In International Conference on Machine learning, 2025. (ICML 2025) [Slides] (* equal contribution)
F. Futami. Epistemic Uncertainty and Excess Risk in Variational Inference. In Artificial Intelligence and Statistics, 2025. (AISTATS 2025) [Slides]
F. Futami*, & M. Fujisawa*. Information-theoretic Generalization Analysis for Expected Calibration Error. In Neural Information Processing Systems, 2024. (NeurIPS 2024) [Slides] (* equal contribution)
F. Futami, & T. Iwata. Information-theoretic Analysis of Test Data Sensitivity in Uncertainty. In Artificial Intelligence and Statistics, 2024. (AISTATS 2024) [Slides]
F. Futami*, & M. Fujisawa*. Time-Independent Information-Theoretic Generalization Bounds for SGLD. In Neural Information Processing Systems, 2023. (NeurIPS 2023)[Slides] (* equal contribution)
F. Futami, T. Iwata, N. Ueda, I. Sato, & M. Sugiyama. Predictive variational Bayesian inference as risk-seeking optimization. In Artificial Intelligence and Statistics, 2022. (AISTATS 2022) [Slides]
F. Futami, T. Iwata, N. Ueda, I. Sato, & M. Sugiyama. Loss function based second-order Jensen inequality and its application to particle variational inference. In Neural Information Processing Systems, 2021. (NeurIPS 2021) [Slides]
F. Futami. Scalable gradient matching based on state space Gaussian Processes. Asian Conference on Machine Learning, 2021. (ACML 2021) [slides]
F. Futami, T. Iwata, N. Ueda, & I. Yamane. Skew-symmetrically perturbed gradient flow for convex optimization. Asian Conference on Machine Learning, 2021. (ACML 2021)[slides]
F. Futami, I. Sato, & M. Sugiyama. Accelerating the diffusion-based ensemble sampling by non-reversible dynamics. International Conference on Machine learning, 2020. (ICML 2020) [Slides]
F. Futami, Z. Cui, I. Sato, & M. Sugiyama. Bayesian posterior approximation via greedy particle optimization, Thirty-Third AAAI Conference on Artificial Intelligence. (AAAI 2019) [Slides]
F. Futami, I. Sato, & M. Sugiyama. Variational Inference based on Robust Divergences. In Artificial Intelligence and Statistics, 2018. (AISTATS 2018) [Slides]
F. Futami, I. Sato, & M. Sugiyama. Expectation Propagation for t-exponential family using q-Algebra. In Neural Information Processing Systems, 2017. (NeurIPS 2017)[Slides]