Consistency of trace norm minimization

Abstract

Regularization by the sum of singular values, also referred to as the trace norm, is a popular technique for estimating low rank rectangular matrices. In this paper, we extend some of the consistency results of the Lasso to provide necessary and sufficient conditions for rank consistency of trace norm minimization with the square loss. We also provide an adaptive version that is rank consistent even when the necessary condition for the non adaptive version is not fulfilled.

References in corpus (14)

• Rejoinder to "Least angle regression" by Efron et al
• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Consistency of the group Lasso and multiple kernel learning
• A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization
• Low-rank matrix factorization with attributes

Cited by in corpus (46)

• Consistency of the group Lasso and multiple kernel learning
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Latent variable graphical model selection via convex optimization
• Estimation of high-dimensional low-rank matrices
• A Unified Framework for High-Dimensional Analysis of M-Estimators with Decomposable Regularizers
• A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization
• Convex Sparse Matrix Factorizations
• Trace Lasso: a trace norm regularization for correlated designs
• Fixed Point and Bregman Iterative Methods for Matrix Rank Minimization
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Local Linear Convergence of Forward-Backward under Partial Smoothness
• Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions
• Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares
• CUR Algorithm for Partially Observed Matrices
• Efficient tensor completion: Low-rank tensor train
• Subsampling Algorithms for Semidefinite Programming
• A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm
• Sharp oracle inequalities for the prediction of a high-dimensional matrix
• Inexact Proximal Gradient Methods for Non-convex and Non-smooth Optimization
• A Fused Latent and Graphical Model for Multivariate Binary Data
• Toward Compact Deep Neural Networks via Energy-Aware Pruning
• Interpreting Latent Variables in Factor Models via Convex Optimization
• Low-rank optimization with trace norm penalty
• Low rank Multivariate regression
• Scalable Interpretable Multi-Response Regression via SEED
• Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation
• A pseudo-RIP for multivariate regression
• Functional Autoregressive Processes in Reproducing Kernel Hilbert Spaces
• Latent variable model selection for Gaussian conditional random fields
• A Rank-Corrected Procedure for Matrix Completion with Fixed Basis Coefficients
• Orthogonal Rank-One Matrix Pursuit for Low Rank Matrix Completion
• Unfolding-Model-Based Visualization: Theory, Method and Applications
• Efficient Online Minimization for Low-Rank Subspace Clustering
• How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?
• Robust Principal Component Analysis with Non-Sparse Errors
• High-dimensional regression with unknown variance
• Factor Analysis on Citation, Using a Combined Latent and Logistic Regression Model
• Increasing Energy Efficiency in Sensor Networks: Blue Noise Sampling and Non-Convex Matrix Completion
• Error Analysis on Graph Laplacian Regularized Estimator
• Sparse Trace Norm Regularization
• Matrix Linear Discriminant Analysis
• Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
• Sparse Empirical Bayes Analysis (SEBA)
• Sharp Threshold for Multivariate Multi-Response Linear Regression via Block Regularized Lasso
• Convex Optimization Methods for Dimension Reduction and Coefficient Estimation in Multivariate Linear Regression
• Nonsmoothness in Machine Learning: specific structure, proximal identification, and applications