当前位置:
X-MOL 学术
›
arXiv.cs.NA
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Consistency analysis of bilevel data-driven learning in inverse problems
arXiv - CS - Numerical Analysis Pub Date : 2020-07-06 , DOI: arxiv-2007.02677 Neil K. Chada, Claudia Schillings, Xin T. Tong and Simon Weissmann
arXiv - CS - Numerical Analysis Pub Date : 2020-07-06 , DOI: arxiv-2007.02677 Neil K. Chada, Claudia Schillings, Xin T. Tong and Simon Weissmann
One fundamental problem when solving inverse problems is how to find
regularization parameters. This article considers solving this problem using
data-driven bilevel optimization, i.e. we consider the adaptive learning of the
regularization parameter from data by means of optimization. This approach can
be interpreted as solving an empirical risk minimization problem, and we
analyze its performance in the large data sample size limit for general
nonlinear problems. To reduce the associated computational cost, online
numerical schemes are derived using the stochastic gradient method. We prove
convergence of these numerical schemes under suitable assumptions on the
forward problem. Numerical experiments are presented illustrating the
theoretical results and demonstrating the applicability and efficiency of the
proposed approaches for various linear and nonlinear inverse problems,
including Darcy flow, the eikonal equation, and an image denoising example.
中文翻译:
逆问题中双层数据驱动学习的一致性分析
求解逆问题时的一个基本问题是如何找到正则化参数。本文考虑使用数据驱动的双层优化来解决这个问题,即我们考虑通过优化的方式从数据中自适应学习正则化参数。这种方法可以解释为解决经验风险最小化问题,我们分析了它在一般非线性问题的大数据样本大小限制下的性能。为了减少相关的计算成本,使用随机梯度方法导出在线数值方案。我们在前向问题的适当假设下证明了这些数值方案的收敛性。
更新日期:2020-07-07
中文翻译:
逆问题中双层数据驱动学习的一致性分析
求解逆问题时的一个基本问题是如何找到正则化参数。本文考虑使用数据驱动的双层优化来解决这个问题,即我们考虑通过优化的方式从数据中自适应学习正则化参数。这种方法可以解释为解决经验风险最小化问题,我们分析了它在一般非线性问题的大数据样本大小限制下的性能。为了减少相关的计算成本,使用随机梯度方法导出在线数值方案。我们在前向问题的适当假设下证明了这些数值方案的收敛性。