Data-driven projection generation for efficiently solving heterogeneous quadratic programming problems

DOI10.1007/S10994-026-07055-5MaRDI QIDQ7298505zbMATH OpenFDO

Authors Tomoharu Iwata, Futoshi Futami

Publication date 16 July 2026

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10994-026-07055-5

Mathematics Subject Classification ID

Graph theory (including graph drawing) in computer science (68R10) Artificial neural networks and deep learning (68T07) Quadratic programming (90C20)

Cites work

• A repository of convex quadratic programming problems
• A theory of learning from different domains
• Convexification with bounded gap for randomly projected quadratic optimization
• CVXPY: a Python-embedded modeling language for convex optimization
• Efficient differentiable quadratic programming layers: an ADMM approach
• Envelope Theorems for Arbitrary Choice Sets
• Foundations of machine learning
• High-dimensional statistics. A non-asymptotic viewpoint
• scientific article; zbMATH DE number 5602305 (Why is no real title available?)
• Learning a classification of mixed-integer quadratic programming problems
• Online Mixed-Integer Optimization in Milliseconds
• OSQP: an operator splitting solver for quadratic programs
• Quadratic programming feature selection
• Random projections for conic programs
• Random projections for quadratic programs
• Random projections for quadratic programs over a Euclidean ball
• Random projections of linear and semidefinite problems with linear inequalities
• Restricted Least Squares Regression and Convex Quadratic Programming

This page was built for publication: Data-driven projection generation for efficiently solving heterogeneous quadratic programming problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7298505)