SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds

SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
复制标题

SoftFlow:流形上流标准化的概率框架

DOI:
--
复制
发表时间:
2020
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
N. Kim
N. Kim
中科院分区:
--
文献类型:
--
作者:
Hyeongju Kim;Hyeonseung Lee;Woohyun Kang;Joun Yeop Lee;N. Kim

文献摘要

参考文献

被引文献

相似文献

基于流的生成模型由相同维度的两个随机变量之间的可逆变换组成。因此,如果数据分布的维度与潜在目标分布的维度不匹配,基于流的模型就无法得到充分训练。在本文中,我们提出了SoftFlow,这是一个在流形上训练归一化流的概率框架。为了避开维度不匹配问题,SoftFlow估计扰动输入数据的条件分布,而不是直接学习数据分布。我们通过实验表明,与传统的基于流的模型不同,SoftFlow能够捕捉流形数据的固有结构并生成高质量的样本。此外,我们将所提出的框架应用于3D点云,以缓解基于流的模型形成精细结构的困难。所提出的3D点云模型,即SoftPointFlow,能够更准确地估计各种形状的分布,并在点云生成方面取得了最先进的性能。
Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match that of the underlying target distribution. In this paper, we propose SoftFlow, a probabilistic framework for training normalizing flows on manifolds. To sidestep the dimension mismatch problem, SoftFlow estimates a conditional distribution of the perturbed input data instead of learning the data distribution directly. We experimentally show that SoftFlow can capture the innate structure of the manifold data and generate high-quality samples unlike the conventional flow-based models. Furthermore, we apply the proposed framework to 3D point clouds to alleviate the difficulty of forming thin structures for flow-based models. The proposed model for 3D point clouds, namely SoftPointFlow, can estimate the distribution of various shapes more accurately and achieves state-of-the-art performance in point cloud generation.
DOI: --
发表时间: 2020-02
期刊: --
影响因子: --
作者:
Danilo Jimenez Rezende;G. Papamakarios;S. Racanière;M. S. Albergo;G. Kanwar;P. Shanahan;Kyle Cranmer
通讯作者: Danilo Jimenez Rezende;G. Papamakarios;S. Racanière;M. S. Albergo;G. Kanwar;P. Shanahan;Kyle Cranmer
可解释的多项式神经常微分方程。
DOI: 10.1063/5.0130803
发表时间: 2023
期刊: Chaos (Woodbury, N.Y.)
影响因子: --
作者:
Fronk,Colby;Petzold,Linda
通讯作者: Petzold,Linda