Low-rank optimization with trace norm penalty
From MaRDI portal
(Redirected from Publication:5408213)
Abstract: The paper addresses the problem of low-rank trace norm minimization. We propose an algorithm that alternates between fixed-rank optimization and rank-one updates. The fixed-rank optimization is characterized by an efficient factorization that makes the trace norm differentiable in the search space and the computation of duality gap numerically tractable. The search space is nonlinear but is equipped with a particular Riemannian structure that leads to efficient computations. We present a second-order trust-region algorithm with a guaranteed quadratic rate of convergence. Overall, the proposed optimization scheme converges super-linearly to the global solution while maintaining complexity that is linear in the number of rows and columns of the matrix. To compute a set of solutions efficiently for a grid of regularization parameters we propose a predictor-corrector approach that outperforms the naive warm-restart approach on the fixed-rank quotient manifold. The performance of the proposed algorithm is illustrated on problems of low-rank matrix completion and multivariate linear regression.
Recommendations
- On the convergence of projected-gradient methods with low-rank projections for smooth convex minimization over trace-norm balls and related problems
- Low-rank matrix completion by Riemannian optimization
- Low-rank factorization for rank minimization with nonconvex regularizers
- Robust low-rank matrix completion by Riemannian optimization
- A Riemannian rank-adaptive method for low-rank matrix completion
Cited in
(33)- Scalable incremental nonconvex optimization approach for phase retrieval
- Riemannian gradient descent methods for graph-regularized matrix completion
- Low-rank dynamic mode decomposition: an exact and tractable solution
- A Riemannian rank-adaptive method for low-rank matrix completion
- Sparse latent factor regression models for genome-wide and epigenome-wide association studies
- Two Newton methods on the manifold of fixed-rank matrices endowed with Riemannian quotient geometries
- Fixed-rank matrix factorizations and Riemannian low-rank optimization
- Nonconvex weak sharp minima on Riemannian manifolds
- Majorized proximal alternating imputation for regularized rank constrained matrix completion
- A Riemannian symmetric rank-one trust-region method
- Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
- Optimization on the hierarchical Tucker manifold - applications to tensor completion
- Low-complexity l₀-norm penalized shrinkage linear and widely linear affine projection algorithms
- Low rank matrix minimization with a truncated difference of nuclear norm and Frobenius norm regularization
- Penalty decomposition methods for rank minimization
- Convergence results for projected line-search methods on varieties of low-rank matrices via Łojasiewicz inequality
- A Riemannian gradient sampling algorithm for nonsmooth optimization on manifolds
- An extended Frank-Wolfe method with ``in-face directions, and its application to low-rank matrix completion
- Harmonic mean iteratively reweighted least squares for low-rank matrix recovery
- Efficient learning with a family of nonconvex regularizers by redistributing nonconvexity
- Generalized conditional gradient for sparse estimation
- Low-rank retractions: a survey and new results
- Riemannian multigrid line search for low-rank problems
- GNMR: a provable one-line algorithm for low rank matrix recovery
- An equivalence between critical points for rank constraints versus low-rank factorizations
- Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
- Orthogonal rank-one matrix pursuit for low rank matrix completion
- On the convergence of projected-gradient methods with low-rank projections for smooth convex minimization over trace-norm balls and related problems
- Sparse reduced-rank regression for simultaneous rank and variable selection via manifold optimization
- Reexamining low rank matrix factorization for trace norm regularization
- Differential geometry with extreme eigenvalues in the positive semidefinite cone
- Implicit low-rank Riemannian schemes for the time integration of stiff partial differential equations
- Semi-blind joint channel estimation and data detection on sphere manifold for MIMO with high-order QAM signaling
This page was built for publication: Low-rank optimization with trace norm penalty
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5408213)
