Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method

DOI10.1109/TIT.2016.2632149zbMath1364.94165arXiv1511.04777OpenAlexW2255205876WikidataQ115263253 ScholiaQ115263253MaRDI QIDQ2989631

No author found.

Publication date: 8 June 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1511.04777

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items

Unnamed Item ⋮ Tracking and Regret Bounds for Online Zeroth-Order Euclidean and Riemannian Optimization ⋮ Unnamed Item ⋮ The local convexity of solving systems of quadratic equations ⋮ Riemannian optimization via Frank-Wolfe methods ⋮ First-order methods almost always avoid strict saddle points ⋮ Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis ⋮ A Trust Region Method for Finding Second-Order Stationarity in Linearly Constrained Nonconvex Optimization ⋮ Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent ⋮ Unnamed Item ⋮ Learning semidefinite regularizers ⋮ Finding a low-rank basis in a matrix subspace ⋮ Unnamed Item ⋮ Nonconvex weak sharp minima on Riemannian manifolds ⋮ A geometric analysis of phase retrieval ⋮ ADMM for multiaffine constrained optimization ⋮ Compressed dictionary learning ⋮ Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions ⋮ Unnamed Item ⋮ Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods ⋮ Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods ⋮ On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint ⋮ An active-set proximal quasi-Newton algorithm for ℓ₁-regularized minimization over a sphere constraint ⋮ Identifiability of Complete Dictionary Learning ⋮ Extending the Step-Size Restriction for Gradient Descent to Avoid Strict Saddle Points ⋮ Geometry and Symmetry in Short-and-Sparse Deconvolution