arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.09800cs.DS
收藏

次二次模函数极小化

Subquadratic Submodular Function Minimization

Deeparnab Chakrabarty, Yin Tat Lee, Aaron Sidford, Sam Chiu-wai Wong

摘要:

次模函数极小化(SFM)是一个基本的离散优化问题,它推广了许多已知的问题,在各个领域都有应用,并且可以在多项式时间内求解。由于在计算机视觉和机器学习中的应用,快速SFM算法是非常需要的。当前最快的算法[Lee,Sidford,Wong,FOCS 2015]分别在$O(n^{2}\log nM\cdot\textrm{EO} +n^{3}\log^{O(1)}nM)$时间和$O(n^{3}\log^{2}n\cdot \textrm{EO} +n^{4}\log^{O(1)}n$)时间内运行,其中$M$是函数的最大绝对值(假设范围是整数),$\textrm{EO}$是在任何集合上计算函数所花费的时间。虽然查询复杂度的最佳下限只有$Ω(n)$,但当前证明函数最优值的最短非确定性证明需要$Θ(n^{2})$函数求值。本文的主要贡献是次二次SFM算法。对于整数值次模函数,我们给出了一个SFM算法,它运行在$O(nM^{3}\log n\cdot\textrm{EO})$时间给出了第一个近线性时间算法在任何已知的制度。对于$[-1,1]$中值域为实数的次模函数,给出了在$\tilde{O}(n^{5/3}\cdot\textrm{EO}/\varepsilon^{2})$时间内返回$\varepsilon$-可加近似解的算法.在它的核心,我们的算法是投影随机次梯度下降方法的次模块化函数的Lovasz扩展,我们至关重要地利用次模块化和数据结构,以获得快速,即次线性时间次梯度更新。.后者是至关重要的击败$n^{2}$的界限,因为我们表明,算法访问仅次梯度的Lovasz扩展,这些包括理论上最好的算法上面提到的,必须使$Ω(n)$次梯度调用(即使是范围为$\{-1,0,1\}$的函数)。

英文摘要:

Submodular function minimization (SFM) is a fundamental discrete optimization problem which generalizes many well known problems, has applications in various fields, and can be solved in polynomial time. Owing to applications in computer vision and machine learning, fast SFM algorithms are highly desirable. The current fastest algorithms [Lee, Sidford, Wong, FOCS 2015] run in $O(n^{2}\log nM\cdot\textrm{EO} +n^{3}\log^{O(1)}nM)$ time and $O(n^{3}\log^{2}n\cdot \textrm{EO} +n^{4}\log^{O(1)}n$) time respectively, where $M$ is the largest absolute value of the function (assuming the range is integers) and $\textrm{EO}$ is the time taken to evaluate the function on any set. Although the best known lower bound on the query complexity is only $Ω(n)$, the current shortest non-deterministic proof certifying the optimum value of a function requires $Θ(n^{2})$ function evaluations. The main contribution of this paper are subquadratic SFM algorithms. For integer-valued submodular functions, we give an SFM algorithm which runs in $O(nM^{3}\log n\cdot\textrm{EO})$ time giving the first nearly linear time algorithm in any known regime. For real-valued submodular functions with range in $[-1,1]$, we give an algorithm which in $\tilde{O}(n^{5/3}\cdot\textrm{EO}/\varepsilon^{2})$ time returns an $\varepsilon$-additive approximate solution. At the heart of it, our algorithms are projected stochastic subgradient descent methods on the Lovasz extension of submodular functions where we crucially exploit submodularity and data structures to obtain fast, i.e. sublinear time subgradient updates. . The latter is crucial for beating the $n^{2}$ bound as we show that algorithms which access only subgradients of the Lovasz extension, and these include the theoretically best algorithms mentioned above, must make $Ω(n)$ subgradient calls (even for functions whose range is $\{-1,0,1\}$).

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。

↑