Genetic column generation for computing lower bounds for adversarial classification

DOI10.1137/24M1678374MaRDI QIDQ6937301zbMATH OpenFDO

Authors

Publication date 27 August 2025

Published in SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1678374

zbMATH Keywords

adversarial robustnessgenetic algorithmmulticlass classificationmultimarginal optimal transport

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Cites work

• An optimal transport approach for computing adversarial training lower bounds in multiclass classification
• Barycenters in the Wasserstein space
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Genetic column generation: fast computation of high-dimensional multimarginal optimal transport problems
• On the existence of solutions to adversarial training in multiclass classification
• Optimal transport: a comprehensive introduction to modeling, analysis, simulation, applications
• Selected Topics in Column Generation
• The \infty-Wasserstein Distance: Local Solutions and Existence of Optimal Transport Maps
• The GenCol Algorithm for High-Dimensional Optimal Transport: General Formulation and Application to Barycenters and Wasserstein Splines
• Understanding and using linear programming

This page was built for publication: Genetic column generation for computing lower bounds for adversarial classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6937301)