Abstract
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 function class, and they do not require prior knowledge about the distribution of training examples or any specific properties of the function class. Using Talagrand's type concentration inequalities for empirical and Rademacher processes, we show that the bounds hold with high probability that decreases exponentially fast when the sample size grows. In typical situations that are frequently encountered in the theory of function learning, the bounds give nearly optimal rate of convergence of the risk to zero.
Keywords
Bounding overwatchFunction (biology)Class (philosophy)MathematicsApplied mathematicsConvergence (economics)Zero (linguistics)Computer scienceArtificial intelligence
Affiliated Institutions
Related Publications
Superlinear Convergence of Primal-Dual Interior Point Algorithms for Nonlinear Programming
The local convergence properties of a class of primal-dual interior point methods are analyzed. These methods are designed to minimize a nonlinear, nonconvex, objective function...
Low-Density Parity-Check Codes
This is a complete presentation of all important theoretical and experimental work done on low-density codes. Low-density coding is one of the three techniques thus far develope...
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the...
Bayesian Density Estimation and Inference Using Mixtures
Abstract We describe and illustrate Bayesian inference in models for density estimation using mixtures of Dirichlet processes. These models provide natural settings for density ...
PANDA: Pose Aligned Networks for Deep Attribute Modeling
We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose...
Publication Info
- Year
- 2000
- Type
- book-chapter
- Pages
- 443-457
- Citations
- 206
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
206
OpenAlex
Cite This
Vladimir Koltchinskii,
Dmitriy Panchenko
(2000).
Rademacher Processes and Bounding the Risk of Function Learning.
Birkhäuser Boston eBooks
, 443-457.
https://doi.org/10.1007/978-1-4612-1358-1_29
Identifiers
- DOI
- 10.1007/978-1-4612-1358-1_29