Zobrazeno 1 - 10
of 131
pro vyhledávání: '"Yang, Minghan"'
Autor:
Shi, Jing, Han, Cunrui, Wang, Tao, Qi, Chao, Chen, Han, Yu, Zhihan, Geng, Jiaqi, Yang, Minghan, Wang, Xu, Chen, Ling, Hui, Hejiu
Seismic anisotropy, arising from the crystallographic or lattice-preferred orientation of anisotropic minerals or the shape-preferred orientation of melts or cracks, can establish a critical link between Mars's past evolution and its current state. S
Externí odkaz:
http://arxiv.org/abs/2405.09120
This paper studies large-scale optimization problems on Riemannian manifolds whose objective function is a finite sum of negative log-probability losses. Such problems arise in various machine learning and signal processing applications. By introduci
Externí odkaz:
http://arxiv.org/abs/2207.07287
In this paper, a novel second-order method called NG+ is proposed. By following the rule ``the shape of the gradient equals the shape of the parameter", we define a generalized fisher information matrix (GFIM) using the products of gradients in the m
Externí odkaz:
http://arxiv.org/abs/2106.07454
Autor:
Cai, Jiao, Yang, Minghan, Zhang, Nan, Chen, Ying, Wei, Jianhua, Wang, Jian, Liu, Qixin, Li, Wenjie, Shi, Wenming, Liu, Wei
Publikováno v:
In Building and Environment 1 March 2024 251
Publikováno v:
In Materials Science & Engineering B January 2024 299
In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true Hessian matrix
Externí odkaz:
http://arxiv.org/abs/2006.09606
In this paper, we develop an efficient sketchy empirical natural gradient method (SENG) for large-scale deep learning problems. The empirical Fisher information matrix is usually low-rank since the sampling is only practical on a small amount of data
Externí odkaz:
http://arxiv.org/abs/2006.05924
In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient of the smooth part of the objective function can only be approximated b
Externí odkaz:
http://arxiv.org/abs/1910.09373
Publikováno v:
In Energy 1 October 2023 280
Publikováno v:
In Applied Thermal Engineering October 2023 233