Relative loss bounds for multidimensional regression problems

Machine Learning

Volumn 45, Issue 3, 2001, Pages 301-329

  Kivinen, J ^a   Warmuth, M K ^b  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^b University of California Santa Cruz   (United States)

Author keywords

Bregman divergences; Generalized linear regression; On line prediction; Relative loss bounds

Indexed keywords

ALGORITHMS; EIGENVALUES AND EIGENFUNCTIONS; TRANSFER FUNCTIONS; VECTORS;

GENERALIZED LINEAR REGRESSIONS;

REGRESSION ANALYSIS;

EID: 0035575628     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1017938623079     Document Type: Article

References (22)

1. Exponentially many local minima for single neurons
2. Relative loss bounds for on-line density estimation with the exponential family of distributions
3. A training algorithm for optimal margin classifiers
4. The relaxation method of finding the common point of convex sets and its applications to the solution of problems in convex programming
5. Some notes on perceptron learning
6. Analysis of two gradient-based algorithms for on-line regression
7. Worst-case quadratic loss bounds for prediction using linear functions and gradient descent
8. On relative loss bounds in generalized linear regression
9. Prediction in the worst case
10. The robustness of the p-norm algorithms
11. Linear hinge loss and average margin
12. General convergence results for linear discriminant updates
13. Covering numbers for support vector machines
14. Relative loss bounds for single neurons
15. Additive versus exponentiated gradient updates for linear prediction
16. The perceptron algorithm vs. winnow: Linear vs. logarithmic mistake bounds when few input variables are relevant
17. Mistake bounds and logarithmic linear-threshold learning algorithms
18. Competitive on-line linear regression