Predictive low rank matrix learning under partial observations: mixed-projection ADMM

DOI10.1007/S10994-026-07005-1MaRDI QIDQ7298517zbMATH OpenFDO

Authors Dimitris Bertsimas, Nicholas A. G. Johnson

Publication date 16 July 2026

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10994-026-07005-1

Mathematics Subject Classification ID

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

Cites work

• 10.1162/153244302760200704
• A unified approach to mixed-integer optimization problems with logical constraints
• Accelerating ill-conditioned low-rank matrix estimation via scaled gradient descent
• Alternating direction method of multipliers for real and complex polynomial optimization models
• An alternating direction algorithm for matrix completion with nonnegative factors
• Augmented Lagrangian alternating direction method for matrix separation based on low-rank factorization
• Bi-cross-validation of the SVD and the nonnegative matrix factorization
• Characterization of the equivalence of robustification and regularization in linear and matrix regression
• Convergence of ADMM for multi-block nonconvex separable optimization models
• Convex relaxations of non-convex mixed integer quadratically constrained programs: Extended formulations
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Global convergence of ADMM in nonconvex nonsmooth optimization
• Guaranteed Matrix Completion via Non-Convex Factorization
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 739533 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 7306912 (Why is no real title available?)
• Linear Matrix Inequalities in System and Control Theory
• Mixed-Projection Conic Optimization: A New Paradigm for Modeling Rank Constraints
• Perspective reformulation and applications
• Robustness and regularization of support vector machines
• Sparse regression: scalable algorithms and empirical performance
• Spectral regularization algorithms for learning large incomplete matrices
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Why Are Big Data Matrices Approximately Low Rank?

This page was built for publication: Predictive low rank matrix learning under partial observations: mixed-projection ADMM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7298517)