Structured Convex Optimization under Submodular Constraints

09/26/2013
by   Kiyohito Nagano, et al.
0

A number of discrete and continuous optimization problems in machine learning are related to convex minimization problems under submodular constraints. In this paper, we deal with a submodular function with a directed graph structure, and we show that a wide range of convex optimization problems under submodular constraints can be solved much more efficiently than general submodular optimization methods by a reduction to a maximum flow problem. Furthermore, we give some applications, including sparse optimization methods, in which the proposed methods are effective. Additionally, we evaluate the performance of the proposed method through computational experiments.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/26/2019

A Memoization Framework for Scaling Submodular Optimization to Large Scale Problems

We are motivated by large scale submodular optimization problems, where ...
01/04/2016

On the Reducibility of Submodular Functions

The scalability of submodular optimization methods is critical for their...
07/10/2014

A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation

A key problem in statistics and machine learning is the determination of...
07/28/2017

Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization

We consider the minimization of submodular functions subject to ordering...
02/17/2021

Joint Continuous and Discrete Model Selection via Submodularity

In model selection problems for machine learning, the desire for a well-...
06/10/2020

Variational Optimization for the Submodular Maximum Coverage Problem

We examine the submodular maximum coverage problem (SMCP), which is rela...
04/18/2022

Optimal Layered Defense For Site Protection

We present a model for layered security with applications to the protect...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.