A model of double descent for high-dimensional binary linear classification
From MaRDI portal
Publication:5095258
DOI10.1093/imaiai/iaab002OpenAlexW3151137625MaRDI QIDQ5095258
Abla Kammoun, Christos Thrampoulidis, Zeyu Deng
Publication date: 5 August 2022
Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1911.05822
empirical risk minimizationoverparameterizationsharp asymptoticsGaussian process inequalitieshard-margin SVM
Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Artificial intelligence (68Txx)
Related Items (7)
Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ High dimensional binary classification under label shift: phase transition and regularization ⋮ Universality of regularized regression estimators in high dimensions ⋮ Unnamed Item ⋮ Large dimensional analysis of general margin based classification methods ⋮ AdaBoost and robust one-bit compressed sensing ⋮ A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
This page was built for publication: A model of double descent for high-dimensional binary linear classification
