Genetic Column Generation for Computing Lower Bounds for Adversarial Classification

Maximilian Penka
6/12/2024
math.NAcs.LG

No confident code implementation found for this paper.

Abstract

Recent theoretical results on adversarial multi-class classification showed a similarity to the multi-marginal formulation of Wasserstein-barycenter in optimal transport. Unfortunately, both problems suffer from the curse of dimension, making it hard to exploit the nice linear program structure of the problems for numerical calculations. We investigate how ideas from Genetic Column Generation for multi-marginal optimal transport can be used to overcome the curse of dimension in computing the minimal adversarial risk in multi-class classification.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification

85% match2024

On the existence of solutions to adversarial training in multiclass classification

77% match2023

Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory

76% match2025

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

75% match1 repo12024

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

75% match1 repo982026

Gromov-Wasserstein and optimal transport: from assignment problems to probabilistic numeric

75% match2025

Cite this paper

@article{penka2024genetic,
  title  = {Genetic Column Generation for Computing Lower Bounds for Adversarial Classification},
  author = {Maximilian Penka},
  year   = {2024},
  eprint = {2406.08331},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.08331v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.08331.svg)](https://codeofpaper.com/paper/2406.08331)

Discussion