Margin-based generalization for classifications with input noise

DOI10.4134/JKMS.J200406MaRDI QIDQ5066176zbMATHFDO

Authors Hi Jun Choe, Hayeong Koh, Jimin Lee

Publication date 29 March 2022

zbMATH Keywords

generalization boundPAC-Bayesianmargin loss function

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Robustness and generalization
• Analysis of classifiers' robustness to adversarial perturbations
• scientific article; zbMATH DE number 7219345
• Convergence rates of generalization errors for margin-based classification
• Theoretical investigation of generalization bounds for adversarial learning of deep neural networks

Cites work

• PAC-Bayesian stochastic model selection
• Simplified PAC-Bayesian margin bounds.
• User-friendly tail bounds for sums of random matrices

Cited in

(2)

• Classification with asymmetric label noise: consistency and maximal denoising
• A note on margin-based loss functions in classification

This page was built for publication: Margin-based generalization for classifications with input noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5066176)