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 1410.5550cs.ITmath.ITmath.PRmath.STstat.TH
收藏

基于相对$α$ -熵II的极小化问题:逆投影

Minimization Problems Based on Relative $α$-Entropy II: Reverse Projection

M. Ashok Kumar, Rajesh Sundaresan

摘要:

在这两部分工作的第一部分中,研究了基于参数族相对熵(表示为$\mathscr{I}_α$)的某些极小化问题。这样的极小化被称为前向$\mathscr{I}_α$ -投影。在这里,一个互补类的最小化问题,导致所谓的反向$\mathscr{I}_α$ -投影进行了研究。反向$\mathscr{I}_α$ -投影,特别是对对数凸或幂律族的投影,在鲁棒估计问题($α>1$)和约束压缩设置($α<1$)中很有意义。首先建立幂律族与相关线性族的正交性,然后利用该正交性将反向$\mathscr{I}_α$ -投影转换为正向$\mathscr{I}_α$ -投影。转换后的问题是一个更简单的拟凸最小化线性约束。

英文摘要:

In part I of this two-part work, certain minimization problems based on a parametric family of relative entropies (denoted $\mathscr{I}_α$) were studied. Such minimizers were called forward $\mathscr{I}_α$-projections. Here, a complementary class of minimization problems leading to the so-called reverse $\mathscr{I}_α$-projections are studied. Reverse $\mathscr{I}_α$-projections, particularly on log-convex or power-law families, are of interest in robust estimation problems ($α>1$) and in constrained compression settings ($α<1$). Orthogonality of the power-law family with an associated linear family is first established and is then exploited to turn a reverse $\mathscr{I}_α$-projection into a forward $\mathscr{I}_α$-projection. The transformed problem is a simpler quasiconvex minimization subject to linear constraints.

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。

↑