Does learning require memorization? a short tale about a long tail

DOI10.1145/3357713.3384290MaRDI QIDQ5144980zbMATH OpenOpenAlexFDO

Authors Vitaly Feldman

Publication date 19 January 2021

Published in Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.05271

zbMATH Keywords

generalizationinterpolationlong-tailed distributionoverfittingprivacy-preserving learning

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cited in

(13)

• Nyström landmark sampling and regularized Christoffel functions
• Switching: understanding the class-reversed sampling in tail sample memorization
• Diversity sampling is an implicit regularization for kernel methods
• scientific article; zbMATH DE number 7626719 (Why is no real title available?)
• scientific article; zbMATH DE number 7625163 (Why is no real title available?)
• Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
• Deep learning: a statistical viewpoint
• On differential privacy and adaptive data analysis with bounded space
• A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors
• Identifying memorization of diffusion models through p-Laplace analysis
• On the robustness of the minimim _2 interpolator
• Provably high degree polynomial representation learning with FreeNets
• Fundamental limits of membership inference attacks on machine learning models

This page was built for publication: Does learning require memorization? a short tale about a long tail

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5144980)