Abstract | ||
---|---|---|
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.
|
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/s10472-018-9613-y | Ann. Math. Artif. Intell. |
Keywords | Field | DocType |
Generalization bounds, Learning theory, Unbounded loss functions, Relative deviation bounds, Importance weighting, Unbounded regression, Machine learning, 97R40 | Discrete mathematics,Mathematical optimization,Weighting,Regression,Mathematical proof,No-arbitrage bounds,Mathematics,Relative standard deviation,Bounded function | Journal |
Volume | Issue | ISSN |
abs/1310.5796 | 1 | 1012-2443 |
Citations | PageRank | References |
7 | 0.53 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Corinna Cortes | 1 | 6574 | 1120.50 |
Spencer Greenberg | 2 | 10 | 1.26 |
Mehryar Mohri | 3 | 4502 | 448.21 |