The Lack of A Priori Distinctions Between Learning Algorithms

@article{Wolpert1996TheLO,
  title={The Lack of A Priori Distinctions Between Learning Algorithms},
  author={D. Wolpert},
  journal={Neural Computation},
  year={1996},
  volume={8},
  pages={1341-1390}
}
  • D. Wolpert
  • Published 1996
  • Mathematics, Computer Science
  • Neural Computation
This is the first of two papers that use off-training set (OTS) error to investigate the assumption-free relationship between learning algorithms. This first paper discusses the senses in which there are no a priori distinctions between learning algorithms. (The second paper discusses the senses in which there are such distinctions.) In this first paper it is shown, loosely speaking, that for any two algorithms A and B, there are as many targets (or priors over targets) for which A has lower… Expand
693 Citations
Domains of competence of the semi-naive Bayesian network classifiers
  • 19
  • PDF
Bias-free hypothesis evaluation in multirelational domains
  • 6
  • Highly Influenced
  • PDF
When is the Naive Bayes approximation not so naive?
  • 7
  • PDF
Attribute Interactions in Machine Learning
  • 28
  • PDF
Exploiting structure defined by data in machine learning : some new analyses
  • PDF
Active Learning Approaches for Labeling Text: Review and Assessment of the Performance of Active Learning Approaches
  • 6
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
On the Connection between In-sample Testing and Generalization Error
  • D. Wolpert
  • Mathematics, Computer Science
  • Complex Syst.
  • 1992
  • 111
  • PDF
Machine learning
  • 13,738
  • PDF
On the monotonicity of the performance of Bayesian classifiers (Corresp.)
  • 35
On Overfitting Avoidance as Bias
  • 142
  • PDF
Exploring the Decision Forest: An Empirical Investigation of Occam's Razor in Decision Tree Induction
  • 88
  • PDF
The Relationship Between PAC, the Statistical Physics Framework, the Bayesian Framework, and the VC Framework
  • 116
Local Algorithms for Pattern Recognition and Dependencies Estimation
  • 102
...
1
2
3
4
5
...