The effect of smooth parametrizations on nonconvex optimization landscapes

Abstract

We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good guarantees) or for theoretical purposes (e.g., to reveal that the landscape satisfies a strict saddle property). In both cases, the central question is: how do the landscapes of the two problems relate? More precisely: how do desirable points such as local minima and critical points in one problem relate to those in the other problem? A key finding in this paper is that these relations are often determined by the parametrization itself, and are almost entirely independent of the cost function. Accordingly, we introduce a general framework to study parametrizations by their effect on landscapes. The framework enables us to obtain new guarantees for an array of problems, some of which were previously treated on a case-by-case basis in the literature. Applications include: optimizing low-rank matrices and tensors through factorizations; solving semidefinite programs via the Burer-Monteiro approach; training neural networks by optimizing their weights and biases; and quotienting out symmetries.

References in corpus (3)

• Low-rank optimization for semidefinite convex problems
• Deterministic guarantees for Burer-Monteiro factorizations of smooth semidefinite programs
• Finding stationary points on bounded-rank matrices: A geometric hurdle and a smooth remedy

Cited by in corpus (6)

• Projected gradient descent accumulates at Bouligand stationary points
• Low-rank optimization methods based on projected projected-gradient descent that accumulate at Bouligand stationary points
• A variable smoothing for Nonconvexly constrained nonsmooth optimization with application to sparse spectral clustering
• Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
• Rigorous Maximum Likelihood Estimation for Quantum States
• The tangent cone to the real determinantal variety: various expressions and a proof