The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound

by   Liam O'Carroll, et al.

The most widely used technique for solving large-scale semidefinite programs (SDPs) in practice is the non-convex Burer-Monteiro method, which explicitly maintains a low-rank SDP solution for memory efficiency. There has been much recent interest in obtaining a better theoretical understanding of the Burer-Monteiro method. When the maximum allowed rank p of the SDP solution is above the Barvinok-Pataki bound (where a globally optimal solution of rank at most p is guaranteed to exist), a recent line of work established convergence to a global optimum for generic or smoothed instances of the problem. However, it was open whether there even exists an instance in this regime where the Burer-Monteiro method fails. We prove that the Burer-Monteiro method can fail for the Max-Cut SDP on n vertices when the rank is above the Barvinok-Pataki bound (p ≥√(2n)). We provide a family of instances that have spurious local minima even when the rank p = n/2. Combined with existing guarantees, this settles the question of the existence of spurious local minima for the Max-Cut formulation in all ranges of the rank and justifies the use of beyond worst-case paradigms like smoothed analysis to obtain guarantees for the Burer-Monteiro method.


page 1

page 2

page 3

page 4


Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form

Semidefinite programs (SDP) are important in learning and combinatorial ...

Improving the smoothed complexity of FLIP for max cut problems

Finding locally optimal solutions for max-cut and max-k-cut are well-kno...

Max-Cut via Kuramoto-type Oscillators

We consider the Max-Cut problem. Let G = (V,E) be a graph with adjacency...

How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?

When the linear measurements of an instance of low-rank matrix recovery ...

Toward Guaranteed Illumination Models for Non-Convex Objects

Illumination variation remains a central challenge in object detection a...

Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality

A number of statistical estimation problems can be addressed by semidefi...

Error Analysis and Correction for Weighted A*'s Suboptimality (Extended Version)

Weighted A* (wA*) is a widely used algorithm for rapidly, but suboptimal...

Please sign up or login with your details

Forgot password? Click here to reset