Zobrazeno 1 - 10
of 596
pro vyhledávání: '"SAKAI, Hiroyuki"'
Autor:
Sakai, Hiroyuki, Iiduka, Hideaki
This 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 lea
Externí odkaz:
http://arxiv.org/abs/2409.00859
What would happen if temperatures were subdued and result in a cool summer? One can easily imagine that air conditioner, ice cream or beer sales would be suppressed as a result of this. Less obvious is that agricultural shipments might be delayed, or
Externí odkaz:
http://arxiv.org/abs/2408.01748
Autor:
Sakai, Hiroyuki, Iiduka, Hideaki
Novel convergence analyses are presented of Riemannian stochastic gradient descent (RSGD) on a Hadamard manifold. RSGD is the most basic Riemannian stochastic optimization algorithm and is used in many applications in the field of machine learning. T
Externí odkaz:
http://arxiv.org/abs/2312.07990
Recent studies on StyleGAN variants show promising performances for various generation tasks. In these models, latent codes have traditionally been manipulated and searched for the desired images. However, this approach sometimes suffers from a lack
Externí odkaz:
http://arxiv.org/abs/2310.00936
Autor:
Sakai, Hiroyuki, Iiduka, Hideaki
This paper presents modified memoryless quasi-Newton methods based on the spectral-scaling Broyden family on Riemannian manifolds. The method involves adding one parameter to the search direction of the memoryless self-scaling Broyden family on the m
Externí odkaz:
http://arxiv.org/abs/2307.08986
Autor:
Harada, Takumi, Sakai, Hiroyuki
Prediction of image memorability has attracted interest in various fields. Consequently, the prediction accuracy of convolutional neural network (CNN) models has been approaching the empirical upper bound estimated based on human consistency. However
Externí odkaz:
http://arxiv.org/abs/2303.07679
This paper presents the Hager-Zhang (HZ)-type Riemannian conjugate gradient method that uses the exponential retraction. We also present global convergence analyses of our proposed method under two kinds of assumptions. Moreover, we numerically compa
Externí odkaz:
http://arxiv.org/abs/2207.01855
Autor:
Iiduka, Hideaki, Sakai, Hiroyuki
This paper considers a stochastic optimization problem over the fixed point sets of quasinonexpansive mappings on Riemannian manifolds. The problem enables us to consider Riemannian hierarchical optimization problems over complicated sets, such as th
Externí odkaz:
http://arxiv.org/abs/2012.09346
Autor:
Nakagawa, Satoshi, Imachi, Hiroyuki, Shimamura, Shigeru, Yanaka, Saeko, Yagi, Hirokazu, Yagi-Utsumi, Maho, Sakai, Hiroyuki, Kato, Shingo, Ohkuma, Moriya, Kato, Koichi, Takai, Ken
Publikováno v:
In BBA Advances 2024 6
Publikováno v:
In Computers in Human Behavior: Artificial Humans January-July 2024 2(1)