Timezone: »

 
Poster
Non-monotone Continuous DR-submodular Maximization: Structure and Algorithms
Yatao Bian · Kfir Levy · Andreas Krause · Joachim M Buhmann

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #162
in Posters Mon »

DR-submodular continuous functions are important objectives with wide real-world applications spanning MAP inference in determinantal point processes (DPPs), and mean-field inference for probabilistic submodular models, amongst others. DR-submodularity captures a subclass of non-convex functions that enables both exact minimization and approximate maximization in polynomial time. In this work we study the problem of maximizing non-monotone DR-submodular continuous functions under general down-closed convex constraints. We start by investigating geometric properties that underlie such objectives, e.g., a strong relation between (approximately) stationary points and global optimum is proved. These properties are then used to devise two optimization algorithms with provable guarantees. Concretely, we first devise a "two-phase'' algorithm with 1/4 approximation guarantee. This algorithm allows the use of existing methods for finding (approximately) stationary points as a subroutine, thus, harnessing recent progress in non-convex optimization. Then we present a non-monotone Frank-Wolfe variant with 1/e approximation guarantee and sublinear convergence rate. Finally, we extend our approach to a broader class of generalized DR-submodular continuous functions, which captures a wider spectrum of applications. Our theoretical findings are validated on synthetic and real-world problem instances.

Keywords: Submodular Optimization · Non-Convex Optimization

Author Information

Yatao Bian (ETH Zürich)
Kfir Levy (ETH)
Andreas Krause (ETH Zurich)
Joachim M Buhmann (ETH Zurich)

More from the Same Authors