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 1204.0649math.FA
收藏

变分正则化格式的必要条件

Necessary conditions for variational regularization schemes

Dirk Lorenz, Nadja Worliczek

摘要:

我们研究变分正则化方法的一般框架,更确切地说,这些方法使用的差异和正则化功能。虽然几组充分条件是已知的,以获得一个正则化方法,我们开始调查的相反的问题:如何可能必要条件的变分方法提供一个正则化方法看起来像?为此,我们形式化的变分方案的概念,并开始比较变分方法的三个不同的实例。然后,我们专注于数据空间模型和研究的作用和相互作用的拓扑结构,收敛的概念和差异功能。特别地,我们推导了偏差泛函满足通常连续性假设的必要条件。这些结果被应用到由Bregman距离给出的差异泛函,特别是Kullback-Leibler发散。

英文摘要:

We study variational regularization methods in a general framework, more precisely those methods that use a discrepancy and a regularization functional. While several sets of sufficient conditions are known to obtain a regularization method, we start with an investigation of the converse question: How could necessary conditions for a variational method to provide a regularization method look like? To this end, we formalize the notion of a variational scheme and start with comparison of three different instances of variational methods. Then we focus on the data space model and investigate the role and interplay of the topological structure, the convergence notion and the discrepancy functional. Especially, we deduce necessary conditions for the discrepancy functional to fulfill usual continuity assumptions. The results are applied to discrepancy functionals given by Bregman distances and especially to the Kullback-Leibler divergence.

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。

↑