REVIEW 2 cited by
From the simplex to the sphere: Faster constrained optimization using the Hadamard parametrization
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
read the original abstract
The standard simplex in R^n, also known as the probability simplex, is the set of nonnegative vectors whose entries sum up to 1. They frequently appear as constraints in optimization problems that arise in machine learning, statistics, data science, operations research, and beyond. We convert the standard simplex to the unit sphere and thus transform the corresponding constrained optimization problem into an optimization problem on a simple, smooth manifold. We show that KKT points and strict-saddle points of the minimization problem on the standard simplex all correspond to those of the transformed problem, and vice versa. So, solving one problem is equivalent to solving the other problem. Then, we propose several simple, efficient, and projection-free algorithms using the manifold structure. The equivalence and the proposed algorithm can be extended to optimization problems with unit simplex, weighted probability simplex, or `1-norm sphere constraints. Numerical experiments between the new algorithms and existing ones show the advantages of the new approach
Forward citations
Cited by 2 Pith papers
-
On Squared-Variable Formulations for Nonlinear Semidefinite programming
Second-order necessary points of the nonsymmetric squared-variable reformulation (SSV or DSS) correspond exactly to weak second-order necessary points of the original semidefinite program (NSDP or BC), without constra...
-
Smooth Reparameterizations of Functions on Simplicial Product Spaces: Applications to Probabilistic Tensor Decomposition and Functional Data Registration
For any elementwise strictly convex ψ with ψ(0)=0, optimizing f over a product of simplices is equivalent in weak second-order KKT sense to optimizing f∘ψ over a product of spheres or similar manifolds.
Discussion (0). Continue with ORCID to comment.