REVIEW 2 cited by
Spurious local minima in nonconvex sum-of-squares optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We study spurious second-order stationary points and local minima in a nonconvex low-rank formulation of sum-of-squares optimization on a real variety $X$. We reformulate the problem of finding a spurious local minimum in terms of syzygies of the underlying linear series, and also bring in topological tools to study this problem. When the variety $X$ is of minimal degree, there exist spurious second-order stationary points if and only if both the dimension and the codimension of the variety are greater than one, answering a question by Legat, Yuan, and Parrilo. Moreover, for surfaces of minimal degree, we provide sufficient conditions to exclude points from being spurious local minima. In particular, all second-order stationary points associated with infinite Gram matrices on the Veronese surface, corresponding to ternary quartics, lie on the boundary and can be written as a binary quartic, up to a linear change of coordinates, complementing work by Scheiderer on decompositions of ternary quartics as a sum of three squares. For general varieties of higher degree, we give examples and characterizations of spurious second-order stationary points in the interior, together with a restricted path algorithm that avoids such points with controlled step sizes, and numerical experiment results illustrating the empirical successes on plane cubic curves and Veronese varieties.
Forward citations
Cited by 2 Pith papers
-
Moment Relaxations for Data-Driven Wasserstein Distributionally Robust Optimization
The paper derives moment (SDP) relaxations for Wasserstein DRO and proves O(r) asymptotic consistency to the empirical problem under degree or boundedness conditions.
-
On quadratic persistence and Pythagoras numbers of totally real projective varieties
For totally real varieties of codimension 3 (degree at least 6) or higher codimension with large degree, next-to-maximal quadratic persistence is equivalent to lying as a codimension-1 subvariety in a variety of minim...
Discussion (0). Continue with ORCID to comment.