文書の過去の版を表示しています。


Publications

  1. preprints (arXiv.org Search Results)
  1. Hideaki Iiduka: Halpern-type Subgradient Methods for Convex Optimization over Fixed Point Sets of Nonexpansive Mappings, Proceedings of International Conference on Nonlinear Analysis and Convex Analysis and International Conference on Optimization: Techniques and Applications -I- pp. 119–125 PDF
  1. Yu Kobayashi, Hideaki Iiduka: Adaptive conjugate gradient method for deep learning, The 2021 Spring National Conference of Operations Research Society of Japan, Tokyo Institute of Technology, Online meeting (Mar. 2, 2021).
  2. Hiroyuki Sakai, Hideaki Iiduka: Extension of adaptive learning rate optimization algorithms to Riemannian manifolds and its application to natural language processing, The 2021 Spring National Conference of Operations Research Society of Japan, Tokyo Institute of Technology, Online meeting (Mar. 2, 2021).
  3. Yini Zhu, Hiroyuki Sakai, Hideaki Iiduka: Training neural networks using adaptive gradient methods, RIMS Workshop on Nonlinear Analysis and Convex Analysis, Research Institute for Mathematical Sciences, Kyoto University, Online meeting (Mar. 1, 2021)
  4. Kanako Shimoyama, Yu Kobayashi, Hideaki Iiduka: Appropriate stochastic gradients used in adaptive learning rate optimization algorithms for training deep neural networks, RIMS Workshop on Nonlinear Analysis and Convex Analysis, Research Institute for Mathematical Sciences, Kyoto University, Online meeting (Mar. 1, 2021)
  1. Kazuhiro Hishinuma: Fixed Point Subgradient Methods for Constrained Nonsmooth Optimization, Meiji University, 2020 PDF
  1. Yu Kobayashi, Hideaki Iiduka: Adaptive optimization method with stochastic conjugate gradient direction and its application to image classification in deep learning, The 2020 Spring National Conference of Operations Research Society of Japan, Nara Kasugano International Forum (Mar. 12, 2020).
  2. Kazuhiro Hishinuma, Hideaki Iiduka: Error evaluation of fixed point quasiconvex subgradient method, The 2020 Spring National Conference of Operations Research Society of Japan, Nara Kasugano International Forum (Mar. 12, 2020).
  3. Haruhi Oishi, Hideaki Iiduka: Resource allocation using fixed point approximation method for 5G network, The 2020 Spring National Conference of Operations Research Society of Japan, Nara Kasugano International Forum (Mar. 12, 2020).
  4. Kengo Shimizu, Hideaki Iiduka: Computational time comparisons for parallel proximal point and subgradient methods for nonsmooth convex optimization over fixed point set of quasi-nonexpansive mapping, The 2020 Spring National Conference of Operations Research Society of Japan, Nara Kasugano International Forum (Mar. 12, 2020).
  5. Hiroyuki Sakai, Hideaki Iiduka: A new conjugate guradient method on Riemann manifold, The 2020 Spring National Conference of Operations Research Society of Japan, Nara Kasugano International Forum (Mar. 12, 2020).
  1. Kazuhiro Hishinuma, Hideaki Iiduka: Applying Conditional Subgradient-like Directions to the Modified Krasnosel’skiĭ-Mann Fixed Point Algorithm Based on the Three-term Conjugate Gradient Method, Proceedings of the 10th International Conference on Nonlinear Analysis and Convex Analysis, pp.59-67 Open Access
  1. Hideaki Iiduka: Convex optimization with complicated constraint and its application, The 2019 Fall National Conference of Operations Research Society of Japan, Higashi Hiroshima Arts & Culture Hall Kurara (Sep. 12, 2019).
  2. Hideaki Iiduka: Fixed point algorithms and their applications, The International Conference on Nonlinear Analysis and Convex Analysis–International Conference on Optimization: Techniques and Applications (NACA-ICOTA2019), Future University Hakodate (Aug. 27, 2019)
  1. Yu Kobayashi, Hideaki Iiduka: Stochastic optimization algorithm using conjugate gradient direction and its application to deep learning, The 2019 Fall National Conference of Operations Research Society of Japan, Higashi Hiroshima Arts & Culture Hall Kurara (Sep. 12, 2019).
  2. Kazuhiro Hishinuma, Hideaki Iiduka: On rate of convergence of fixed point subgradient method, The 2019 Fall National Conference of Operations Research Society of Japan, Higashi Hiroshima Arts & Culture Hall Kurara (Sep. 12, 2019).
  3. Kengo Shimizu, Hideaki Iiduka: Nonsmooth convex optimization over fixed point sets of quasi nonexpansive mappings by using parallel proximal point algorithm, The 2019 Fall National Conference of Operations Research Society of Japan, Higashi Hiroshima Arts & Culture Hall Kurara (Sep. 12, 2019).
  4. Kazuhiro Hishinuma, Hideaki Iiduka: Convergence rate analyses of fixed point quasiconvex subgradient method, The International Conference on Nonlinear Analysis and Convex Analysis–International Conference on Optimization: Techniques and Applications (NACA-ICOTA2019), Future University Hakodate (Aug. 27, 2019)
  1. Hideaki Iiduka: Decentralized Optimization and Its Applications, the 6th Asian Conference on Nonlinear Analysis and Optimization, ANA Intercontinental Manza Beach Resort (Nov. 6, 2018)
  1. Kazuhiro Hishinuma, Hideaki Iiduka: Convergence property, computational performance, and usability of fixed point quasiconvex subgradient method, the 6th Asian Conference on Nonlinear Analysis and Optimization, Okinawa Institute of Science and Technology Graduate University (Nov. 7, 2018)
  2. Yu Kobayashi, Hideaki Iiduka: Stochastic subgradient projection method for nonmonotone equilibrium problems and its application to multi class classification, the 6th Asian Conference on Nonlinear Analysis and Optimization, Okinawa Institute of Science and Technology Graduate University (Nov. 5, 2018)
  3. Hideo Yoshizato, Hideaki Iiduka: Stochastic fixed point optimization algorithm for classifier ensemble with sparsity and diversity learning and its application, the 6th Asian Conference on Nonlinear Analysis and Optimization, Okinawa Institute of Science and Technology Graduate University (Nov. 5, 2018)
  4. Yu Kobayashi, Hideaki Iiduka: Stochastic subgradient method for stochastic equilibrium problems with nonmonotone bifunctions and its application to multiclass classification, RIMS Workshop on Nonlinear Analysis and Convex Analysis, Research Institute for Mathematical Sciences, Kyoto University (Aug. 29, 2018)
  5. Kazuhiro Hishinuma, Hideaki Iiduka: Application of incremental and parallel subgradient methods to learning a support vector machine and its advantages and disadvantages, The 2018 Spring National Conference of Operations Research Society of Japan, Tokai University (Mar. 15, 2018).
  6. Hideo Yoshizato, Hideaki Iiduka: Stochastic fixed point optimization algorithm for ensemble learning with sparsity and diversity, The 2018 Spring National Conference of Operations Research Society of Japan, Tokai University (Mar. 15, 2018).
  1. Hideaki Iiduka: Nonsmooth Convex Optimization With Fixed Point Constraints and Its Applications, Proceedings of the Twenty-Ninth RAMP Symposium, pp. 125–142, 2017.
  1. Hideaki Iiduka: Nonsmooth Convex Optimization With Fixed Point Constraints and Its Applications, The 29th RAMP (Research Association of Mathematical Programming) Symposium, Tsukuba University, Tsukuba, Japan, October 12-13, 2017.
  1. Kazuhiro Hishinuma, Hideaki Iiduka: Iterative method for solving constrained quasiconvex optimization problems based on the Krasnosel'skiĭ-Mann fixed point approximation method, RIMS Workshop on Nonlinear Analysis and Convex Analysis, Research Institute for Mathematical Sciences, Kyoto University (Sep. 1, 2017)
  2. Kazuhiro Hishinuma, Hideaki Iiduka: Quasi-subgradient method for quasiconvex minimization problem with fixed point constraints, the RIMS Workshop on Development of Mathematical Optimization: Modeling and Algorithms, Research Institute for Mathematical Sciences, Kyoto University (Aug. 25 2017)
  3. Kazuhiro Hishinuma, Hideaki Iiduka: Flexible stepsize selection of subgradient methods for constrained convex optimization, the 10th Anniversary Conference on Nonlinear Analysis and Convex Analysis, Chitose City Cultural Center (Jul. 7, 2017)
  1. Kazuhiro Hishinuma, Hideaki Iiduka: Acceleration approach for parallel subgradient method based on line search, The 2016 Fall National Conference of Operations Research Society of Japan, Yamagata University (Sept. 15-16 2016)
  2. Kaito Sakurai, Hideaki Iiduka: Parallel computing method for nonsmooth convex optimization with fixed point constraints, The 2016 Fall National Conference of Operations Research Society of Japan, Yamagata University (Sept. 15-16 2016)
  3. Yoshiharu Nohara, Hideaki Iiduka: Line search subgradient methods for convex optimization problem and its dual problem, The 2016 Fall National Conference of Operations Research Society of Japan, Yamagata University (Sept. 15-16 2016)
  4. Takayuki Jimba, Kaito Sakurai, Hideaki Iiduka: Halpern-type proximal point algorithm for nonsmooth convex optimization with fixed point constraints, The 2016 Fall National Conference of Operations Research Society of Japan, Yamagata University (Sept. 15-16 2016)
  5. Shizuka Nishino, Hideaki Iiduka: Numerical methods for nonnegative matrix factorization based on fixed point theory, The 2016 Fall National Conference of Operations Research Society of Japan, Yamagata University (Sept. 15-16 2016)
  1. Kazuhiro Hishinuma, Hideaki Iiduka: On Acceleration of the Krasnosel’skii-Mann Fixed Point Algorithm Based on Conjugate Gradient Method for Smooth Optimization, Journal of Nonlinear and Convex Analysis: Special Issue-Dedicated to Wataru Takahashi on the occasion of his 70th birth day 16 (11): 2243-2254 (2015) Open Access PDF
  2. Masato Uchida, Hideaki Iiduka, Isao Sugino: Modeling User Behavior in P2P Data Storage System, IEICE Transactions on Communications: Special Section on Quality of Diversifying Communication Networks and Services E98-B (1): 33-41 (2015) PDF
  1. Kazuhiro Hishinuma, Hideaki Iiduka: Parallel Computing Method for Nonsmooth Convex Optimization, RIMS Kôkyûroku No.1963, pp.71–77 Open Access
  1. Kazuhiro Hishinuma, Hideaki Iiduka: On Parallel Computing Method for Nonsmooth Convex Optimization, The 2014 Fall National Conference of Operations Research Society of Japan, Hokkaido University of Science (Aug. 28-29 2014)
  2. Kazuhiro Hishinuma, Hideaki Iiduka: Parallel Algorithm for Nonsmooth Convex Optimization, The International Workshop on Nonlinear Analysis and Convex Analysis, Research Institute for Mathematical Sciences, Kyoto University (Aug. 19-21 2014)
  • en/intro/publications.1626149659.txt.gz
  • 最終更新: 2021/07/13 13:14
  • by Hideaki IIDUKA