Publications

Refereed Papers in Journals

  1. S. Takahashi, M. Tanaka, and S. Ikeda:
    Majorization-minimization Bregman proximal gradient algorithms for NMF with the Kullback–Leibler divergence, Journal of Optimization Theory and Applications  208(14), (2026). [arXiv] [codes]
  2. S. Takahashi and A. Takeda:
    Approximate Bregman proximal gradient algorithm for relatively smooth nonconvex optimization, Computational Optimization and Applications  90(1), 227–256 (2025). [arXiv] [codes]
  3. S. Takahashi, M. Tanaka, and S. Ikeda:
    Blind deconvolution with non-smooth regularization via Bregman proximal DCAs, Signal Processing  202, 108734 (2023). [arXiv]
  4. S. Takahashi, M. Fukuda, and M. Tanaka:
    New Bregman proximal type algorithms for solving DC optimization problems, Computational Optimization and Applications  83(3), 893–931 (2022). [arXiv] [codes]

Refereed Proceedings in Conferences

  1. S. Takahashi, S. Pokutta, and A. Takeda:
    Fast Frank–Wolfe algorithms with adaptive Bregman step-size for weakly convex functions, in Proceedings of the 14th International Conference on Learning Representations  (ICLR 2026), 2026. [poster] [slide] [info] [arXiv]

Preprints

  1. S. Takahashi:
    Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration, arXiv:2601.20443 (2026). [arXiv] 
  2. K. Fujiki, S. Takahashi, and A. Takeda:
    Approximate Bregman proximal gradient algorithm with variable metric Armijo–Wolfe line search, arXiv:2510.06615 (2025). [arXiv] [codes]

Conferences

  1. S. Takahashi:
    Majorization-minimization Bregman proximal gradient algorithms for NMF with the Kullback–Leibler divergence, Workshop on Data Science for Inverse Problems and Sensing, Tokyo, Japan, March 2026.
  2. S. Takahashi:
    Accelerated Convergence of Frank–Wolfe Algorithms with Adaptive Bregman Step-Size Strategy, The 8th International Conference on Continuous Optimization, Los Angeles, U.S., July 2025. (Session Organizer: Fast Algorithms for Data Science)
  3. S. Takahashi and A. Takeda:
    Approximate Bregman proximal gradient algorithm for relatively smooth nonconvex optimization, The 25th International Symposium on Mathematical Programming, Montreal, Canada, July 2024. (Session Organizer: Gradient-based methods: theory and advances)
  4. S. Takahashi:
    Bregman proximal DC algorithms and their application to blind deconvolution with nonsmooth regularization, 2023 SIAM Conference on Optimization, Seattle, Washington, U.S., May 2023.
  5. S. Takahashi:
    Bregman proximal DC algorithms and their application to blind deconvolution with nonsmooth regularization, International Workshop on Continuous Optimization, online, December 2022.
  6. S. Takahashi:
    Bregman proximal DC algorithms and their application to blind deconvolution with nonsmooth regularization, The 6th RIKEN-IMI-ISM-NUS-ZIB-MODAL-NHR Workshop on Advances in Classical and Quantum Algorithms for Optimization and Machine Learning, Tokyo, Japan, September 2022.
  7. S. Takahashi, M. Fukuda, and M. Tanaka:
    New Bregman proximal type algorithms for solving DC optimization problems, EUROPT 2021 18th Workshop on Advances in Continuous Optimization, online, July 2021.
  8. S. Takahashi, and M. Fukuda:
    New Bregman proximal type algorithms for solving DC optimization problems, INFORMS Optimization Society Conference 2020, Greenville, South Carolina, U.S., March 2020.
    (cancelled due to COVID-19)