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 2403.16208math.NAcs.LGcs.NA
收藏

用于样本生成的 OT-Flow 的收敛性分析

Convergence analysis of OT-Flow for sample generation

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Mathematical Sciences, Shanghai Jiao Tong University(上海交通大学数学科学学院)

Yang Jing, Lei Li

AI总结:

本文为深度生成模型 OT-Flow 建立了严格的理论收敛证明,通过重构模型框架证明了其向最优传输问题的 Γ-收敛性,并利用蒙特卡洛方法与神经网络逼近能力给出了离散与连续损失函数间的收敛性及上界。

摘要:

深度生成模型旨在学习数据的底层分布并生成新数据。尽管生成模型具有多样性且在实践中具有高质量的生成性能,但大多数模型缺乏严格的理论收敛证明。在这项工作中,我们旨在为深度生成模型之一 OT-Flow 建立一些收敛性结果。首先,通过重构 OT-Flow 模型的框架,我们确立了当正则化项参数 $α$ 趋于无穷大时,OT-flow 的公式表示向相应的最优传输(OT)问题的 $Γ$-收敛性。其次,由于在训练中损失函数将由蒙特卡洛方法近似,我们还证明了当样本数 $N$ 趋于无穷大时,离散损失函数与连续损失函数之间的收敛性。同时,神经网络的逼近能力为极小值的离散损失函数提供了上界。这两个方面的证明为 OT-Flow 提供了令人信服的保证。

英文摘要:

Deep generative models aim to learn the underlying distribution of data and generate new ones. Despite the diversity of generative models and their high-quality generation performance in practice, most of them lack rigorous theoretical convergence proofs. In this work, we aim to establish some convergence results for OT-Flow, one of the deep generative models. First, by reformulating the framework of OT-Flow model, we establish the $Γ$-convergence of the formulation of OT-flow to the corresponding optimal transport (OT) problem as the regularization term parameter $α$ goes to infinity. Second, since the loss function will be approximated by Monte Carlo method in training, we established the convergence between the discrete loss function and the continuous one when the sample number $N$ goes to infinity as well. Meanwhile, the approximation capability of the neural network provides an upper bound for the discrete loss function of the minimizers. The proofs in both aspects provide convincing assurances for OT-Flow.

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。

↑