Unified Acceleration Method for Packing and Covering Problems via Diameter Reduction

TitleUnified Acceleration Method for Packing and Covering Problems via Diameter Reduction
Publication TypeConference Paper
Year of Publication2015
AuthorsWang, D., Rao S., & Mahoney M. W.
Published inProceedings of the 43rd ICALP Conference

The linear coupling method was introduced recently by Allen-Zhu and Orecchia for solving convex optimization problems with first order methods, and it provides a conceptually simple way to integrate a gradient descent step and mirror descent step in each iteration. The high-level approach of the linear coupling method is very flexible, and it has shown initial promise by providing improved algorithms for packing and covering linear programs. Somewhat surprisingly, however, while the dependence of the convergence rate on the error parameter ϵ for packing problems was improved to O(1/ϵ), which corresponds to what accelerated gradient methods are designed to achieve, the dependence for covering problems was only improved to O(1/ϵ1.5), and even that required a different more complicated algorithm. Given the close connections between packing and covering problems and since previous algorithms for these very related problems have led to the same ϵ dependence, this discrepancy is surprising, and it leaves open the question of the exact role that the linear coupling is playing in coordinating the complementary gradient and mirror descent step of the algorithm. In this paper, we clarify these issues for linear coupling algorithms for packing and covering linear programs, illustrating that the linear coupling method can lead to improved O(1/ϵ) dependence for both packing and covering problems in a unified manner, i.e., with the same algorithm and almost identical analysis. Our main technical result is a novel diameter reduction method for covering problems that is of independent interest and that may be useful in applying the accelerated linear coupling method to other combinatorial problems.


DW was supported by ARO Grant W911NF-12-1-0541, SR was funded by NSF Grant CCF-1118083, and MM acknowledges the support of the NSF, AFOSR,and DARPA.

ICSI Research Group

Big Data