Adversarially robust learning with tolerance

MaRDI QIDQ7022771zbMATH OpenFDO

Authors Hassan Ashtiani, Vinayak Pathak, Ruth Urner

Publication date 24 February 2025

Full work available at URL https://proceedings.mlr.press/v201/ashtiani23a.html

zbMATH Keywords

adversarial perturbationsPAC-learningperturband-S sample compressiontolerant adversarial robustness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• -nets and simplex range queries
• A theory of the learnable
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Every complete doubling metric space carries a doubling measure
• Improved generalization bounds for robust learning
• Learnability and the Vapnik-Chervonenkis dimension
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Random smoothing might be unable to certify \(\ell_\infty\) robustness for high-dimensional images
• Sample Compression Schemes for VC Classes
• The optimal sample complexity of PAC learning
• Understanding machine learning. From theory to algorithms

This page was built for publication: Adversarially robust learning with tolerance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7022771)