Continuous Submodular Maximization: Beyond DR-Submodularity

06/21/2020
by   Moran Feldman, et al.
0

In this paper, we propose the first continuous optimization algorithms that achieve a constant factor approximation guarantee for the problem of monotone continuous submodular maximization subject to a linear constraint. We first prove that a simple variant of the vanilla coordinate ascent, called Coordinate-Ascent+, achieves a (e-1/2e-1-ε)-approximation guarantee while performing O(n/ε) iterations, where the computational complexity of each iteration is roughly O(n/√(ε)+nlog n) (here, n denotes the dimension of the optimization problem). We then propose Coordinate-Ascent++, that achieves the tight (1-1/e-ε)-approximation guarantee while performing the same number of iterations, but at a higher computational complexity of roughly O(n^3/ε^2.5 + n^3 log n / ε^2) per iteration. However, the computation of each round of Coordinate-Ascent++ can be easily parallelized so that the computational cost per machine scales as O(n/√(ε)+nlog n).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2018

Unconstrained Submodular Maximization with Constant Adaptive Complexity

In this paper, we consider the unconstrained submodular maximization pro...
research
04/24/2018

Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization

This paper considers stochastic optimization problems for a large class ...
research
05/24/2018

Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization

In this paper we study the fundamental problems of maximizing a continuo...
research
10/16/2018

Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization

In this paper, we study the problem of monotone (weakly) DR-submodular c...
research
01/28/2019

Black Box Submodular Maximization: Discrete and Continuous Settings

In this paper, we consider the problem of black box continuous submodula...
research
05/19/2018

Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference

Mean field inference in probabilistic models is generally a highly nonco...
research
02/19/2019

Stochastic Conditional Gradient++

In this paper, we develop Stochastic Continuous Greedy++ (SCG++), the fi...

Please sign up or login with your details

Forgot password? Click here to reset