Online learning in the embedded manifold of low-rank matrices

MaRDI QIDQ5405124zbMATH OpenFDO

Authors Uri Shalit, Daphna Weinshall, Gal Chechik

Publication date 1 April 2014

Full work available at URL http://www.jmlr.org/papers/v13/shalit12a.html

zbMATH Keywords

Riemannian manifoldsmetric learningonline learninglow rankmultitask learningretractions

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Learning and adaptive systems in artificial intelligence (68T05) Vector spaces, linear dependence, rank, lineability (15A03)

Recommendations

• Low-rank kernel learning with Bregman matrix divergences
• Low-Rank Online Metric Learning
• Low-rank matrix completion by Riemannian optimization
• Fixed-rank matrix factorizations and Riemannian low-rank optimization
• Active subspace: toward scalable low-rank learning

Cited in

(22)

• A geometric approach to dynamical model order reduction
• Generalization bounds for metric and similarity learning
• Analysis of asymptotic escape of strict saddle sets in manifold optimization
• Low-Rank Online Metric Learning
• Convergence results for projected line-search methods on varieties of low-rank matrices via Łojasiewicz inequality
• Online local learning via semidefinite programming
• Implicit low-rank Riemannian schemes for the time integration of stiff partial differential equations
• Fixed-rank matrix factorizations and Riemannian low-rank optimization
• Online manifold regularization by dual ascending procedure
• Robust PCA by manifold optimization
• Low-rank bilinear classification: efficient convex optimization and extensions
• Online learning for matrix factorization and sparse coding
• Geometric Methods on Low-Rank Matrix and Tensor Manifolds
• Low-rank retractions: a survey and new results
• Input perturbations for adaptive control and learning
• On adaptive linear-quadratic regulators
• Improved Estimation of High-dimensional Additive Models Using Subspace Learning
• Active subspace: toward scalable low-rank learning
• Structured learning of binary codes with column generation for optimizing ranking measures
• Riemannian multigrid line search for low-rank problems
• Nonconvex weak sharp minima on Riemannian manifolds
• The geometry of algorithms using hierarchical tensors

Describes a project that uses

Uses Software

• ImageNet

This page was built for publication: Online learning in the embedded manifold of low-rank matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405124)