Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning

DOI10.1137/090763184zbMath1211.90129OpenAlexW2045704273WikidataQ57511264 ScholiaQ57511264MaRDI QIDQ3083339

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

zbMATH Keywords

convex optimizationsemidefinite programmingdualitymulti-task learningproximal gradient methodgene expression pattern analysistrace norm regularization

Mathematics Subject Classification ID

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

Related Items (21)

Low-Rank and Sparse Multi-task Learning ⋮ A distributed Frank-Wolfe framework for learning low-rank matrices with the trace norm ⋮ Distributed multi-task classification: a decentralized online learning approach ⋮ Unnamed Item ⋮ Robust reduced rank regression in a distributed setting ⋮ A smoothing stochastic gradient method for composite optimization ⋮ Multistage Convex Relaxation Approach to Rank Regularized Minimization Problems Based on Equivalent Mathematical Program with a Generalized Complementarity Constraint ⋮ Proximal linearization methods for Schatten \(p\)-quasi-norm minimization ⋮ Smooth over-parameterized solvers for non-smooth structured optimization ⋮ Calibrated multi-task subspace learning via binary group structure constraint ⋮ Stochastic Saddle Point Problems with Decision-Dependent Distributions ⋮ Adaptive and robust multi-task learning ⋮ A sparsity preserving stochastic gradient methods for sparse regression ⋮ A partial proximal point algorithm for nuclear norm regularized matrix least squares problems ⋮ Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization ⋮ Regularization-based model tree for multi-output regression ⋮ Unnamed Item ⋮ Supervised Learning by Support Vector Machines ⋮ A constrained matrix-variate Gaussian process for transposable data ⋮ Generalized Conditional Gradient for Sparse Estimation ⋮ Kernel collaborative online algorithms for multi-task learning

Uses Software

• RCV1

This page was built for publication: Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning