Relative deviation learning bounds and generalization with 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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Annals of mathematics and artificial intelligence Ročník 85; číslo 1; s. 45 - 70
Hlavní autoři: Cortes, Corinna, Greenberg, Spencer, Mohri, Mehryar
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 01.01.2019
Springer
Springer Nature B.V
Témata:
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
ISSN:1012-2443, 1573-7470
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 the loss is bounded. We then illustrate how to apply these results in a sample application: the analysis of importance weighting.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1012-2443
1573-7470
DOI:10.1007/s10472-018-9613-y