The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension

Abstract

Non-convex methods for linear inverse problems with low-dimensional models have emerged as an alternative to convex techniques. We propose a theoretical framework where both finite dimensional and infinite dimensional linear inverse problems can be studied. We show how the size of the the basins of attraction of the minimizers of such problems is linked with the number of available measurements. This framework recovers known results about low-rank matrix estimation and off-the-grid sparse spike estimation, and it provides new results for Gaussian mixture estimation from linear measurements. keywords: low-dimensional models, non-convex methods, low-rank matrix recovery, off-the-grid sparse recovery, Gaussian mixture model estimation from linear measurements.

References in corpus (15)

• High-Dimensional Data Clustering
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Global rates of convergence for nonconvex optimization on manifolds
• Global Optimality of Local Search for Low Rank Matrix Recovery
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
• Fundamental performance limits for ideal decoders in high-dimensional linear inverse problems
• On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
• The Non-convex Geometry of Low-rank Matrix Optimization
• The basins of attraction of the global minimizers of the non-convex sparse spike estimation problem
• Projected gradient descent for non-convex sparse spike estimation
• Alternatives to the EM Algorithm for ML-Estimation of Location, Scatter Matrix and Degree of Freedom of the Student-$t$ Distribution
• Native Banach spaces for splines and variational inverse problems
• Measuring the Accuracy of Object Detectors and Trackers
• Recipes for stable linear embeddings from Hilbert spaces to R^m

Cited by in corpus (6)

• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• Wasserstein Patch Prior for Image Superresolution
• WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution
• Large Scale Clustering with Variational EM for Gaussian Mixture Models
• Sparse Mixture Models inspired by ANOVA Decompositions
• Stochastic Super-Resolution For Gaussian Textures