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 1304.5218math.NAcs.NA
收藏

最小二乘正则化与ℓ0范数的极小解描述。全局极小解的唯一性

Description of the minimizers of least squares regularized~ with~ $\bm{\ell_0}$-norm. Uniqueness of the global minimizer

CMLA, ENS Cachan, CNRS(CMLA, 巴黎高等师范学校卡尚分校, 法国国家科学研究中心)

Mila Nikolova

AI总结:

本文研究了结合二次数据保真项和ℓ0惩罚项的目标函数极小解,分析了极小解的唯一性及计算方法,揭示了正则化参数对极小解稀疏性的影响。

摘要:

我们有一个实值任意矩阵A(例如字典)和数据d,用于描述目标对象。本文深入分析了结合二次数据保真项和ℓ0惩罚项的目标函数Fd的(局部和全局)极小解。经过几十年的努力,人们不断尝试设计算法接近一个好的极小解。本文的理论贡献表明,现有算法得到新的启示,并有助于创新数值方案的构思。对于任何A的m行子矩阵的正规方程求解等价于计算Fd的局部极小解。局部极小解hu严格当且仅当由hu支持集的列组成的子矩阵具有满列秩。结果表明,严格局部极小解可以通过不考虑正则化参数be的值轻松计算。每个严格局部极小解线性于数据。证明了Fd具有全局极小解且总是严格。在标准假设下,研究了A的秩为m< n时的全局极小解。具有m长度支持的全局极小解被认为是不实际的。对于任意k≤m-1,给出临界值be_k,当be>be_k时,所有Fd的全局极小解都是k-稀疏的。假设A的某些性质被采用并证明只在可忽略的闭集上失效。对于所有数据d超出可忽略的闭集,当be>be_k,k≤m-1时,Fd有唯一的全局极小解,且该极小解是k-稀疏的。有教育意义的小规模(5×10)数值示例验证了主要理论结果。

英文摘要:

We have an $\m\x\n$ real-valued arbitrary matrix $A$ (e.g. a dictionary) with $\m<\n$ and data $d$ describing the sought-after object with the help of $A$. This work provides an in-depth analysis of the (local and global) minimizers of an objective function $\Fd$ combining a quadratic data-fidelity term and an $\ell_0$ penalty applied to each entry of the sought-after solution, weighted by a regularization parameter $\be>0$. For several decades, this objective has attracted a ceaseless effort to conceive algorithms approaching a good minimizer. Our theoretical contributions, summarized below, shed new light on the existing algorithms and can help the conception of innovative numerical schemes. To solve the normal equation associated with any $\m$-row submatrix of $A$ is equivalent to compute a local minimizer $\hu$ of $\Fd$. (Local) minimizers $\hu$ of $\Fd$ are strict if and only if the submatrix, composed of those columns of $A$ whose indexes form the support of $\hu$, has full column rank. An outcome is that strict local minimizers of $\Fd$ are easily computed without knowing the value of $\be$. Each strict local minimizer is linear in data. It is proved that $\Fd$ has global minimizers and that they are always strict. They are studied in more details under the (standard) assumption that $\rank(A)=\m<\n$. The global minimizers with $\m$-length support are seen to be impractical. Given $d$, critical values $\be_\k$ for any $\k\leq\m-1$ are exhibited such that if $\be>\be_\k$, all global minimizers of $\Fd$ are $\k$-sparse. An assumption on $A$ is adopted and proved to fail only on a closed negligible subset. Then for all data $d$ beyond a closed negligible subset, the objective $\Fd$ for $\be>\be_\k$, $\k\leq\m-1$, has a unique global minimizer and this minimizer is $\k$-sparse. Instructive small-size ($5\x 10$) numerical illustrations confirm the main theoretical results.

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。

↑