ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels (Q2209821)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels |
scientific article |
Statements
ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels (English)
0 references
5 November 2020
0 references
regularized empirical risk minimizers (RERM)
0 references
outliers
0 references
robustness
0 references
minimax-rate-optimality
0 references
0 references
0 references
0 references
0 references