A new analytical approach to consistency and overfitting in regularized empirical risk minimization

DOI10.1017/S0956792517000201zbMath1383.49029arXiv1607.00274MaRDI QIDQ3133606

Ryan W. Murray, Nicolás García Trillos

Publication date: 5 February 2018

Published in: European Journal of Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1607.00274

zbMATH Keywords

classification; empirical risk minimization; overfitting; discrete to continuum; graph total variation

Mathematics Subject Classification ID

62G20: Asymptotic properties of nonparametric inference

68R10: Graph theory (including graph drawing) in computer science

49J45: Methods involving semicontinuity and convergence; relaxation

49J55: Existence of optimal solutions to problems involving randomness