A Riemannian rank-adaptive method for low-rank matrix completion
From MaRDI portal
Publication:2070331
Abstract: The low-rank matrix completion problem can be solved by Riemannian optimization on a fixed-rank manifold. However, a drawback of the known approaches is that the rank parameter has to be fixed a priori. In this paper, we consider the optimization problem on the set of bounded-rank matrices. We propose a Riemannian rank-adaptive method, which consists of fixed-rank optimization, rank increase step and rank reduction step. We explore its performance applied to the low-rank matrix completion problem. Numerical experiments on synthetic and real-world datasets illustrate that the proposed rank-adaptive method compares favorably with state-of-the-art algorithms. In addition, it shows that one can incorporate each aspect of this rank-adaptive framework separately into existing algorithms for the purpose of improving performance.
Recommendations
- Low-rank matrix completion by Riemannian optimization
- Riemannian gradient descent methods for graph-regularized matrix completion
- Robust low-rank matrix completion by Riemannian optimization
- Guarantees of Riemannian optimization for low rank matrix completion
- Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
Cites work
- scientific article; zbMATH DE number 5223994 (Why is no real title available?)
- A brief introduction to manifold optimization
- Convergence results for projected line-search methods on varieties of low-rank matrices via Łojasiewicz inequality
- Geometric Methods on Low-Rank Matrix and Tensor Manifolds
- Global rates of convergence for nonconvex optimization on manifolds
- Guarantees of Riemannian optimization for low rank matrix recovery
- Low rank matrix completion by alternating steepest descent methods
- Low-rank matrix completion by Riemannian optimization
- Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
- Low-rank optimization with trace norm penalty
- Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
- Riemannian Optimization on the Symplectic Stiefel Manifold
- The Riemannian Barzilai-Borwein method with nonmonotone line search and the matrix geometric mean computation
- Two-Point Step Size Gradient Methods
Cited in
(18)- Guarantees of Riemannian optimization for low rank matrix completion
- A universal rank approximation method for matrix completion
- Low-rank optimization with trace norm penalty
- An adaptation for iterative structured matrix completion
- Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
- A Riemannian Framework for Low-Rank Structured Elliptical Models
- A feasible method for general convex low-rank SDP problems
- Low-rank tensor methods for partial differential equations
- Stable Rank-Adaptive Dynamically Orthogonal Runge–Kutta Schemes
- Adaptive and Implicit Regularization for Matrix Completion
- Riemannian gradient descent methods for graph-regularized matrix completion
- Fixed-rank matrix factorizations and Riemannian low-rank optimization
- Robust low-rank matrix completion by Riemannian optimization
- Riemannian conjugate gradient methods: general framework and specific algorithms with convergence analyses
- Low-rank matrix completion by Riemannian optimization
- Low-rank retractions: a survey and new results
- T-product factorization based method for matrix and tensor completion problems
- Fully adaptive structure-preserving hyper-reduction of parametric Hamiltonian systems
This page was built for publication: A Riemannian rank-adaptive method for low-rank matrix completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2070331)
