19299 research outputs found
Sort by
Lectures for those who stay home "3D Optical Illusion - 8. Invisible Chicken"
No full text研究成果としての錯視作品を素材に用いた立体錯視の講
Lectures for those who stay home "3D Optical Illusion - 13. Ambiguous Tiling"
No full text研究成果としての錯視作品を素材に用いた立体錯視の講
外出自粛で退屈している人のための自主講座「不可能立体の世界 ２．反重力斜面」
No full textLecture series on 3D optical illusions, using Kokichi Sugihara's research results as material
外出自粛で退屈している人のための自主講座「不可能立体の世界 ９．変身立体」
No full textLecture series on 3D optical illusions, using Kokichi Sugihara's research results as material
A general framework of Riemannian adaptive optimization methods with a convergence analysis
No full textThis paper proposes a general framework of Riemannian adaptive optimization methods. The framework encapsulates several stochastic optimization algorithms on Riemannian manifolds and incorporates the mini-batch strategy that is often used in deep learning. Within this framework, we also propose AMSGrad on embedded submanifolds of Euclidean space. Moreover, we give convergence analyses valid for both a constant and a diminishing step size. Our analyses also reveal the relationship between the convergence rate and mini-batch size. In numerical experiments, we applied the proposed algorithm to principal component analysis and the low-rank matrix completion problem, which can be considered to be Riemannian optimization problems. Python implementations of the methods used in the numerical experiments are available at https://github.com/iiduka-researches/202408-adaptive. © 2025, Transactions on Machine Learning Research. All rights reserved.journal articl