广义Bregman距离
The Generalized Bregman Distance
摘要:
最近,一个新的距离已被引入到两个点到集算子,其中一个是最大单调的图。当两个算子都是一个适当的下连续凸函数的次微分时,这个距离在适当的假设下特殊化为经典的Bregman距离。我们将这种新的距离命名为广义Bregman距离,并通过利用另外两个最自然的代表函数:Fitzpatrick函数及其共轭函数的例子来阐明它。我们提供了充分条件的凸性,超凸性,超凸性:属性是必不可少的近点型算法的实施。我们建立这些结果的左和右变量的这个新的距离。我们构建的例子密切相关的Kullback-Leibler分歧,这是以前考虑的背景下,布雷格曼距离,其重要性在信息论是众所周知的。在这样做,我们演示了如何计算一个困难的Fitzpatrick共轭函数,我们发现自然发生的兰伯特$\W$功能,其重要性在优化是越来越感兴趣。
英文摘要:
Recently, a new distance has been introduced for the graphs of two point-to-set operators, one of which is maximally monotone. When both operators are the subdifferential of a proper lower semicontinuous convex function, this distance specializes under modest assumptions to the classical Bregman distance. We name this new distance the generalized Bregman distance, and we shed light on it with examples that utilize the other two most natural representative functions: the Fitzpatrick function and its conjugate. We provide sufficient conditions for convexity, coercivity, and supercoercivity: properties that are essential for implementation in proximal point type algorithms. We establish these results for both the left and right variants of this new distance. We construct examples closely related to the Kullback--Leibler divergence, which was previously considered in the context of Bregman distances, and whose importance in information theory is well known. In so doing, we demonstrate how to compute a difficult Fitzpatrick conjugate function, and we discover natural occurrences of the Lambert $\W$ function, whose importance in optimization is of growing interest.
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。