Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Zhu, Huminhao"'
Wasserstein Gradient Flows (WGF) with respect to specific functionals have been widely used in the machine learning literature. Recently, neural networks have been adopted to approximate certain intractable parts of the underlying Wasserstein gradien
Externí odkaz:
http://arxiv.org/abs/2401.14069
Particle-based Variational Inference (ParVI) methods approximate the target distribution by iteratively evolving finite weighted particle systems. Recent advances of ParVI methods reveal the benefits of accelerated position update strategies and dyna
Externí odkaz:
http://arxiv.org/abs/2312.16429
Autor:
Wang, Fangyikang1 (AUTHOR) wangfangyikang@zju.edu.cn, Zhu, Huminhao1 (AUTHOR), Zhang, Chao1 (AUTHOR) zczju@zju.edu.cn, Zhao, Hanbin1 (AUTHOR), Qian, Hui1 (AUTHOR)
Publikováno v:
Entropy. Aug2024, Vol. 26 Issue 8, p679. 44p.