Gradient descent with non-convex constraints: local concavity determines convergence
From MaRDI portal
Publication:5242862
DOI10.1093/imaiai/iay002zbMath1476.90251arXiv1703.07755OpenAlexW2963925364WikidataQ130162676 ScholiaQ130162676MaRDI QIDQ5242862
Rina Foygel Barber, Wooseok Ha
Publication date: 7 November 2019
Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1703.07755
Related Items (7)
Orientation estimation of cryo-EM images using projected gradient descent method ⋮ Unnamed Item ⋮ Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy ⋮ Gradient projection method on matrix manifolds ⋮ An Equivalence between Critical Points for Rank Constraints Versus Low-Rank Factorizations ⋮ Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach ⋮ The gradient projection algorithm for smooth sets and functions in nonconvex case
This page was built for publication: Gradient descent with non-convex constraints: local concavity determines convergence
