Kyohei Suzuki

Kyohei Suzuki

Assistant Professor at Institute of Science Tokyo, Department of Information and Communications Engineering and the Human Centered Science and Biomedical Engineering Major

Member of Prof. Slavakis's laboratory

Publications

Link to Google Scholar Citations

Link to T2R2

Preprint

  1. K. Haishima, K. Suzuki, and K. Slavakis, “External Division of Two Bregman Proximity Operators for Poisson Inverse Problems,” arXiv:2602.11482, 2026.
  2. K. Suzuki and K. Slavakis, “Nonconvex Regularization for Feature Selection in Reinforcement Learning,” arXiv:2509.15652, 2025.

Journal Articles

  1. K. Suzuki and M. Yukawa, “External Division of Two Proximity Operators—Part II: Generalization and Properties,” IEEE Trans. Signal Process., vol. 74, pp. 167-182, 2026. official access
  2. K. Suzuki and M. Yukawa, “External Division of Two Proximity Operators—Part I: Debiased Feature Grouping,” IEEE Trans. Signal Process., vol. 74, pp. 150-166, 2026. official access
  3. M. Yukawa, H. Kaneko, K. Suzuki, and I. Yamada, “Linearly-Involved Moreau-Enhanced-Over-Subspace Model: Debiased Sparse Modeling and Stable Outlier-Robust Regression,” IEEE Trans. Signal Process., vol. 71, pp. 1232–1247, 2023. official access
  4. K. Suzuki and M. Yukawa, “Sparse Stable Outlier-Robust Signal Recovery Under Gaussian Noise,” IEEE Trans. Signal Process., vol. 71, pp. 372–387, 2023. official access
  5. K. Suzuki and M. Yukawa, “Robust Recovery of Jointly-Sparse Signals Using Minimax Concave Loss Function,” IEEE Trans. Signal Process., vol. 69, pp. 669–681, 2021 (publication: Dec. 2020). official access

Peer-Reviewed Conference Proceedings

  1. K. Suzuki and K. Slavakis, “Nonconvex Regularization for Feature Selection in Reinforcement Learning,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Barcelona, Spain, 2026, accepted.
  2. K. Suzuki and M. Yukawa, “Sparse Signal Recovery Based on Lower-semicontinuous 1-weakly-convex Envelope of a Marginal Function,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Barcelona, Spain, 2026, accepted.
  3. K. Suzuki and M. Yukawa, “A discrete measure for debiased feature grouping: A limit of Moreau-enhanced OSCAR regularizer and its proximity operator,” in Proc. Eur. Signal Process. Conf. (EUSIPCO), pp. 2467–2471, Palermo, Italy, 2025. official access
  4. K. Suzuki and M. Yukawa, “External Division of Two Proximity Operators: An Application to Signal Recovery with Structured Sparsity,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Seoul, Korea, pp. 9471–9475, Apr. 2024. official access
  5. M. Yukawa, K. Suzuki, and I. Yamada, “Stable Robust Regression under Sparse Outlier and Gaussian Noise,” in Proc. Eur. Signal Process. Conf. (EUSIPCO), pp. 2236–2240, Aug.–Sep. 2022. official access
  6. K. Suzuki and M. Yukawa, “Sparse Stable Outlier-Robust Regression with Minimax Concave Function,” in Proc. IEEE Int. Workshop Mach. Learn. Signal Process. (MLSP), 6 pages, Aug. 2022. official access
  7. K. Suzuki and M. Yukawa, “On Grouping Effect of Sparse Stable Outlier-Robust Regression,” in Proc. IEEE Int. Workshop Mach. Learn. Signal Process. (MLSP), 6 pages, Aug. 2022. official access
  8. K. Suzuki and M. Yukawa, “Robust Jointly-Sparse Signal Recovery Based on Minimax Concave Loss Function,” in Proc. Eur. Signal Process. Conf. (EUSIPCO), pp. 2070–2074, Jan. 2021. official access

Non-Peer-Reviewed Articles

  1. K. Suzuki and K. Slavakis, “Feature Selection in Reinforcement Learning via Projected Minimax Concave Penalty,” in Proc. IEICE Signal Processing Symposium, Ibaraki, Japan, 6 pages, Nov. 2025.
  2. K. Suzuki and M. Yukawa, “On the Proximity Operator of the Lower-semicontinuous 1-weakly-convex Envelope of a Marginal Function,” in Proc. IEICE Signal Processing Symposium, Ibaraki, Japan, 6 pages, Nov. 2025.
  3. K. Suzuki and M. Yukawa, “Bias Reduction for Feature Grouping Based on a Limit of Moreau-Enhanced OSCAR Regularizer,” in Proc. IEICE Signal Processing Symposium, Sapporo, Japan, 6 pages, Dec. 2024.
  4. T. Okuda, K. Suzuki, and M. Yukawa, “Sparse Signal Recovery Based on Continuous Relaxation of Reversely Ordered Weighted ℓ₁ Shrinkage Operator,” in Proc. IEICE Signal Processing Symposium, Sapporo, Japan, 6 pages, Dec. 2024.
  5. K. Suzuki and M. Yukawa, “Debiased Estimation of Signals with Structured Sparsity Based on External Division of Two Proximity Operators,” in Proc. IEICE Signal Processing Symposium, Kyoto, Japan, 6 pages, Nov. 2023.
  6. K. Suzuki and M. Yukawa, “Multiscale Manifold Clustering and Embedding with Multiple Kernels,” in Proc. IEICE Tech. Rep., vol. 122, no. 388, SIP2022-167, pp. 276–281, Okinawa, Japan, Mar. 2023.
  7. K. Suzuki and M. Yukawa, “Sparse Stable Outlier-Robust Regression Using Minimax Concave Function,” in Proc. IEICE Signal Processing Symposium, pp. 96–101, virtual (Zoom), Nov. 2021.
  8. K. Suzuki and M. Yukawa, “A Robust Approach to Jointly-Sparse Signal Recovery Based on Minimax Concave Loss Function,” in Proc. IEICE Tech. Rep., vol. 119, no. 440, SIP2019-124, pp. 123–128, Okinawa, Japan (conference cancelled), Mar. 2020.

Talks

  1. 鈴木京平, “ガウス性雑音環境下でのスパース安定頑健信号復元法”, 第22回情報科学技術フォーラム（FIT2023）, 大阪府堺市, 2023年9月, 招待講演.

Doctoral Dissertation

  1. K. Suzuki, “A study of robust debiasing methods for sparse modeling: Moreau enhancement and beyond,” Doctoral dissertation, Keio University, Sept. 2024. official access