arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.15048cs.LGphysics.comp-ph
收藏

基于物理反演的尺度不变学习

Scale-invariant Learning by Physics Inversion

Technical University of Munich(慕尼黑工业大学);Apple(苹果公司)

Philipp Holl, Vladlen Koltun, Nils Thuerey

摘要:

求解逆问题,如参数估计和最优控制,是科学的重要组成部分。许多实验重复收集数据并依赖机器学习算法来快速推断相关逆问题的解决方案。我们发现,国家的最先进的培训技术并不适合许多问题,涉及物理过程。物理过程中常见的高度非线性行为导致强烈变化的梯度,导致SGD或Adam等一阶优化器计算次优优化方向。我们提出了一种新的混合训练方法,结合高阶优化方法与机器学习技术。我们从尺度不变的逆问题求解器中获取更新,并将其嵌入到基于梯度下降的学习管道中,取代物理过程的常规梯度。我们证明了我们的方法在各种规范的物理系统的能力,表明它产生了显着的改进,在广泛的优化和学习问题。

英文摘要:

Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse problems. We find that state-of-the-art training techniques are not well-suited to many problems that involve physical processes. The highly nonlinear behavior, common in physical processes, results in strongly varying gradients that lead first-order optimizers like SGD or Adam to compute suboptimal optimization directions. We propose a novel hybrid training approach that combines higher-order optimization methods with machine learning techniques. We take updates from a scale-invariant inverse problem solver and embed them into the gradient-descent-based learning pipeline, replacing the regular gradient of the physical process. We demonstrate the capabilities of our method on a variety of canonical physical systems, showing that it yields significant improvements on a wide range of optimization and learning problems.

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。

↑