A Faster Randomized Algorithm for Vertex Cover: An Automated Approach
By: Katie Clinch , Serge Gaspers , Tao Zixu He and more
Potential Business Impact:
Makes computers solve hard puzzles much faster.
This work introduces two techniques for the design and analysis of branching algorithms, illustrated through the case study of the Vertex Cover problem. First, we present a method for automatically generating branching rules through a systematic case analysis of local structures. Second, we develop a new technique for analyzing randomized branching algorithms using the Measure & Conquer method, offering greater flexibility in formulating branching rules. By combining these innovations with additional techniques, we obtain the fastest known randomized algorithms in different parameters for the Vertex Cover problem on graphs with bounded degree (up to 6) and on general graphs. For example, our algorithm solves Vertex Cover on subcubic graphs in $O^*(1.07625^n)$ time and $O^*(1.13132^k)$ time, respectively. For graphs with maximum degree 4, we achieve running times of $O^*(1.13735^n)$ and $O^*(1.21103^k)$, while for general graphs we achieve $O^*(1.25281^k)$.
Similar Papers
Addressing Bias in Algorithmic Solutions: Exploring Vertex Cover and Feedback Vertex Set
Data Structures and Algorithms
Finds fair solutions for everyone, not just most.
A Learning Perspective on Random-Order Covering Problems
Data Structures and Algorithms
Helps computers solve problems faster by learning.
Fast Stochastic Greedy Algorithm for $k$-Submodular Cover Problem
Data Structures and Algorithms
Makes smart computer tasks faster and cheaper.