Multiclass Clustering using a Semidefinite Relaxation
نویسنده
چکیده
We propose a semidefinite relaxation for graph clustering known as Max-cut clustering. The clustering problem is formulated in terms of a discrete optimization problem and then relaxed to a SDP. The SDP is solved using a low-rank factorization trick that reduces the number of variables, and then using a simple projected gradient method. This is joint work with Nathan Srebro at the Toyota Technology Institute-Chicago and part of research was performed at the Toyota Technology Institute-Chicago.
منابع مشابه
A semidefinite relaxation scheme for quadratically constrained
Semidefinite optimization relaxations are among the widely used approaches to find global optimal or approximate solutions for many nonconvex problems. Here, we consider a specific quadratically constrained quadratic problem with an additional linear constraint. We prove that under certain conditions the semidefinite relaxation approach enables us to find a global optimal solution of the unde...
متن کاملSemidefinite spectral clustering
Multi-way partitioning of an undirected weighted graph where pairwise similarities are assigned as edge weights, provides an important tool for data clustering, but is an NP-hard problem. Spectral relaxation is a popular way of relaxation, leading to spectral clustering where the clustering is performed by the eigen-decomposition of the (normalized) graph Laplacian. On the other hand, semidefin...
متن کاملApproximating Quadratic Programs with Semidefinite Relaxations
Given an arbitrary matrix A in which all of the diagonal elements are zero, we would like to find x1, x2, . . . , xn ∈ {−1, 1} such that ∑n i=1 ∑n j=1 aijxixj is maximized. This problem has an important application in correlation clustering, and is also related to the well-known inequality of Grothendieck in functional analysis. While solving quadratic programs is NP-hard, we can approximate th...
متن کاملOptimization of Multiclass Queueing Networks with Changeover times via the Achievable Region Approach: Part I, the Single-station Case
We address the performance optimization problem in a single-station multiclass queueing network with changeover times by means of the achievable region approach. This approach seeks to obtain performance bounds and scheduling policies from the solution of a mathematical program over a relaxation of the system’s performance region. Relaxed formulations (including linear, convex, nonconvex and po...
متن کاملClustering subgaussian mixtures by semidefinite programming
We introduce a model-free relax-and-round algorithm for k-means clustering based on a semidefinite relaxation due to Peng and Wei [PW07]. The algorithm interprets the SDP output as a denoised version of the original data and then rounds this output to a hard clustering. We provide a generic method for proving performance guarantees for this algorithm, and we analyze the algorithm in the context...
متن کامل