Max Cut and the Smallest Eigenvalue

TL;DR

This paper introduces a spectral partitioning-based approximation algorithm for Max Cut that runs in nearly quadratic time, achieving over 53% approximation ratio and effectively handling instances close to optimal solutions.

Contribution

It presents a novel spectral partitioning method for Max Cut with nearly linear time complexity, improving approximation ratios for near-optimal instances.

Findings

Achieves a 0.531 approximation ratio in ilde O(n^2) time.

Finds solutions close to optimal in graphs with high edge cut fractions.

Provides a spectral approach analogous to Cheeger's inequality for the smallest eigenvalue.

Abstract

We describe a new approximation algorithm for Max Cut. Our algorithm runs in $\tilde O(n^2)$ time, where $n$ is the number of vertices, and achieves an approximation ratio of $.531$. On instances in which an optimal solution cuts a $1-\epsilon$ fraction of edges, our algorithm finds a solution that cuts a $1-4\sqrt{\epsilon} + 8\epsilon-o(1)$ fraction of edges. Our main result is a variant of spectral partitioning, which can be implemented in nearly linear time. Given a graph in which the Max Cut optimum is a $1-\epsilon$ fraction of edges, our spectral partitioning algorithm finds a set $S$ of vertices and a bipartition $L,R=S-L$ of $S$ such that at least a $1-O(\sqrt \epsilon)$ fraction of the edges incident on $S$ have one endpoint in $L$ and one endpoint in $R$. (This can be seen as an analog of Cheeger's inequality for the smallest eigenvalue of the adjacency matrix of a graph.) Iterating this procedure yields the approximation results stated above. A different, more complicated, variant of spectral partitioning leads to an $\tilde O(n^3)$ time algorithm that cuts $1/2 + e^{-\Omega(1/\eps)}$ fraction of edges in graphs in which the optimum is $1/2 + \epsilon$.