arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.13619stat.MLcs.LG
收藏

通过最小化Wasserstein-2损失进行生成建模

Generative Modeling by Minimizing the Wasserstein-2 Loss

Department of Applied Mathematics, University of Colorado(应用数学系,科罗拉多大学)

Yu-Jui Huang, Zachariah Malik

AI总结:

本文提出通过分布依赖的常微分方程最小化Wasserstein-2损失来构建生成模型,证明其时间边际律构成Wasserstein损失的梯度流,并通过欧拉方案实现收敛,实验表明算法在低维和高维情况下优于Wasserstein生成对抗网络。

摘要:

本文发展了一种生成模型,通过分布依赖的常微分方程最小化第二阶Wasserstein损失(W₂损失)。该方程的动力学涉及与真实数据分布相关的Kantorovich势能以及当前估计的势能。主要结果表明,方程的时间边际律构成W₂损失的梯度流,能够指数收敛到真实数据分布。提出了一种欧拉方案用于该方程,并证明其在极限情况下能恢复W₂损失的梯度流。通过遵循该方案并应用持续训练,设计出一种算法,自然适应我们的梯度流方法。在低维和高维实验中,该算法通过适当增加持续训练水平,优于Wasserstein生成对抗网络。

英文摘要:

This paper develops a generative model by minimizing the second-order Wasserstein loss (the $W_2$ loss) through a distribution-dependent ordinary differential equation (ODE), whose dynamics involves the Kantorovich potential associated with the true data distribution and a current estimate of it. A main result shows that the time-marginal laws of the ODE form a gradient flow for the $W_2$ loss, which converges exponentially to the true data distribution. An Euler scheme for the ODE is proposed and it is shown to recover the gradient flow for the $W_2$ loss in the limit. An algorithm is designed by following the scheme and applying persistent training, which naturally fits our gradient-flow approach. In both low- and high-dimensional experiments, our algorithm outperforms Wasserstein generative adversarial networks by increasing the level of persistent training appropriately.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑