Relative deviation learning bounds and generalization with unbounded loss functions

• Published in: Annals of mathematics and artificial intelligence Vol. 85; no. 1; pp. 45 - 70
• Main Authors: Cortes, Corinna, Greenberg, Spencer, Mohri, Mehryar
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.01.2019; Springer; Springer Nature B.V
• Subjects: Analysis; Artificial Intelligence; Complex Systems; Computer Science; Deviation; Expected values; Inequality; Machine learning; Mathematics; Probability; Random variables; Relative deviation bounds; Unbounded regression; Machine learning; Importance weighting; Generalization bounds; Learning theory; 97R40; Unbounded loss functions

We present an extensive analysis of relative deviation bounds, including detailed proofs of two-sided inequalities and their implications. We also give detailed proofs of two-sided generalization bounds that hold in the general case of unbounded loss functions, under the assumption that a moment of...