Keywords
Computer scienceGaussianBounded functionClass (philosophy)Basis (linear algebra)Function (biology)Gaussian functionArtificial neural networkTheoretical computer scienceMathematical optimizationAlgorithmArtificial intelligenceMathematics
Affiliated Institutions
Related Publications
Rademacher Processes and Bounding the Risk of Function Learning
We construct data dependent upper bounds on the risk in function learning problems. The bounds are based on local norms of the Rademacher process indexed by the underlying funct...
Comparing top k lists
Motivated by several applications, we introduce various distance measures between k lists. Some of these distance measures are metrics, while others are not. For each of these ...
Multilevel models with multivariate mixed response types
We build upon the existing literature to formulate a class of models for multivariate mixtures of Gaussian, ordered or unordered categorical responses and continuous distributio...
Causal Inference, Path Analysis, and Recursive Structural Equations Models
Rubin's model for causal inference in experiments and observational studies is enlarged to analyze the problem of “causes causing causes” and is compared to path analysis and re...
On the generalization of soft margin algorithms
Generalization bounds depending on the margin of a classifier are a relatively new development. They provide an explanation of the performance of state-of-the-art learning syste...
Publication Info
- Year
- 2001
- Type
- book-chapter
- Pages
- 224-240
- Citations
- 2107
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
2107
OpenAlex
Cite This
Peter L. Bartlett,
Shahar Mendelson
(2001).
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results.
Lecture notes in computer science
, 224-240.
https://doi.org/10.1007/3-540-44581-1_15
Identifiers
- DOI
- 10.1007/3-540-44581-1_15