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 2306.04895stat.MLcs.LG
收藏

使用具有全梯度惩罚的条件生成对抗网络求解基于物理的逆问题

Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty

University of Maryland(马里兰大学);University of Southern California(南加州大学)

Deep Ray, Javier Murgoitio-Esandi, Agnimitra Dasgupta, Assad A. Oberai

AI总结:

本文提出带全梯度惩罚的 cWGAN,使 critic 同时对待推断向量和测量向量满足 1-Lipschitz,从而更准确稳健地求解基于物理的高维概率逆问题。

摘要:

求解相应正问题受物理原理约束的概率逆问题具有挑战性。当待推断向量的维度很大,且关于它的先验信息以样本集合的形式存在时,尤其如此。在本工作中,开发了一种新颖的基于深度学习的方法,并将其应用于求解此类问题。该方法利用从先验分布中抽取的待推断向量样本以及基于物理的正模型,为条件 Wasserstein 生成对抗网络(cWGAN)生成训练数据。cWGAN 学习以测量值为条件的待推断向量的概率分布,并从该分布中生成样本。本工作开发的 cWGAN 与早期版本的不同之处在于,要求其 critic 相对于待推断向量和测量向量均为 1-Lipschitz,而不仅相对于前者。这产生了一个带有全梯度惩罚(而非部分梯度惩罚)的损失项。结果表明,这一相当简单的改动为 cWGAN 学习到的条件密度带来了更强的收敛概念,并形成了更稳健、更准确的采样策略。通过数值算例表明,该改动在求解逆问题时也转化为更高的精度。所考虑的数值算例包括真实分布和/或统计量已知的说明性问题,以及一个由生物力学应用推动的更复杂的逆问题。

英文摘要:

The solution of probabilistic inverse problems for which the corresponding forward problem is constrained by physical principles is challenging. This is especially true if the dimension of the inferred vector is large and the prior information about it is in the form of a collection of samples. In this work, a novel deep learning based approach is developed and applied to solving these types of problems. The approach utilizes samples of the inferred vector drawn from the prior distribution and a physics-based forward model to generate training data for a conditional Wasserstein generative adversarial network (cWGAN). The cWGAN learns the probability distribution for the inferred vector conditioned on the measurement and produces samples from this distribution. The cWGAN developed in this work differs from earlier versions in that its critic is required to be 1-Lipschitz with respect to both the inferred and the measurement vectors and not just the former. This leads to a loss term with the full (and not partial) gradient penalty. It is shown that this rather simple change leads to a stronger notion of convergence for the conditional density learned by the cWGAN and a more robust and accurate sampling strategy. Through numerical examples it is shown that this change also translates to better accuracy when solving inverse problems. The numerical examples considered include illustrative problems where the true distribution and/or statistics are known, and a more complex inverse problem motivated by applications in biomechanics.

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。

↑