Trace norm regularization: reformulations, algorithms, and multi-task learning

DOI10.1137/090763184zbMATH Open1211.90129OpenAlexW2045704273WikidataQ57511264 ScholiaQ57511264MaRDI QIDQ3083339FDOQ3083339

Authors: Ting Kei Pong, Shuiwang Ji, Jieping Ye, Paul Tseng 

Publication date: 21 March 2011

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/090763184

Recommendations

• Regularization techniques for learning with matrices
• Sparse trace norm regularization
• On spectral learning
• Consistency of trace norm minimization
• Least square regularized regression for multitask learning

zbMATH Keywords

convex optimizationmulti-task learningproximal gradient methodsemidefinite programmingdualitygene expression pattern analysistrace norm regularization

Mathematics Subject Classification ID

Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Applications of mathematical programming (90C90) Protein sequences, DNA sequences (92D20) Semidefinite programming (90C22)

Cited In (26)

• Regularization-based model tree for multi-output regression
• Generalized conditional gradient for sparse estimation
• Smooth over-parameterized solvers for non-smooth structured optimization
• Supervised Learning by Support Vector Machines
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Title not available (Why is that?)
• Proximal linearization methods for Schatten \(p\)-quasi-norm minimization
• A distributed Frank-Wolfe framework for learning low-rank matrices with the trace norm
• Multistage convex relaxation approach to rank regularized minimization problems based on equivalent mathematical program with a generalized complementarity constraint
• A sparsity preserving stochastic gradient methods for sparse regression
• Robust reduced rank regression in a distributed setting
• Matrix completion from a computational statistics perspective
• Distributed multi-task classification: a decentralized online learning approach
• Kernel collaborative online algorithms for multi-task learning
• Adaptive and robust multi-task learning
• A partial proximal point algorithm for nuclear norm regularized matrix least squares problems
• Mixed-integer quadratic programming reformulations of multi-task learning models
• Stochastic Saddle Point Problems with Decision-Dependent Distributions
• On spectral learning
• Sparse trace norm regularization
• A constrained matrix-variate Gaussian process for transposable data
• Low-rank and sparse multi-task learning
• Regularization techniques for learning with matrices
• A smoothing stochastic gradient method for composite optimization
• Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization
• Calibrated multi-task subspace learning via binary group structure constraint

Uses Software

• RCV1

This page was built for publication: Trace norm regularization: reformulations, algorithms, and multi-task learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3083339)