Iiduka, Hideaki

10 publications

TMLR 2025 A General Framework of Riemannian Adaptive Optimization Methods with a Convergence Analysis Hiroyuki Sakai, Hideaki Iiduka

ACML 2025 Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum Using Increasing Batch Size Kento Imaizumi, Hideaki Iiduka

AAAI 2025 Explicit and Implicit Graduated Optimization in Deep Neural Networks Naoki Sato, Hideaki Iiduka

ACML 2025 Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size Kanata Oowada, Hideaki Iiduka

ACML 2025 Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum Keisuke Kamo, Hideaki Iiduka

TMLR 2025 Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent Hikaru Umeda, Hideaki Iiduka

TMLR 2025 Relationship Between Batch Size and Number of Steps Needed for Nonconvex Optimization of Stochastic Gradient Descent Using Armijo-Line-Search Learning Rate Yuki Tsukada, Hideaki Iiduka

JMLR 2024 Scaled Conjugate Gradient Method for Nonconvex Optimization in Deep Neural Networks Naoki Sato, Koshiro Izumi, Hideaki Iiduka

AISTATS 2023 Conjugate Gradient Method for Generative Adversarial Networks Hiroki Naganuma, Hideaki Iiduka

ICML 2023 Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule Naoki Sato, Hideaki Iiduka