Greedy Minimization of Weakly Supermodular Set Functions

23 Feb 2015  ·  Boutsidis Christos, Liberty Edo, Sviridenko Maxim ·

This paper defines weak-$\alpha$-supermodularity for set functions. Many optimization objectives in machine learning and data mining seek to minimize such functions under cardinality constrains... We prove that such problems benefit from a greedy extension phase. Explicitly, let $S^*$ be the optimal set of cardinality $k$ that minimizes $f$ and let $S_0$ be an initial solution such that $f(S_0)/f(S^*) \le \rho$. Then, a greedy extension $S \supset S_0$ of size $|S| \le |S_0| + \lceil \alpha k \ln(\rho/\varepsilon) \rceil$ yields $f(S)/f(S^*) \le 1+\varepsilon$. As example usages of this framework we give new bicriteria results for $k$-means, sparse regression, and columns subset selection. read more

PDF Abstract
No code implementations yet. Submit your code now

Categories


Data Structures and Algorithms

Datasets


  Add Datasets introduced or used in this paper