Corpus ID: 16597958

Notes on Learning with Irrelevant Attributes in the PAC Model

@inproceedings{Dhagat1994NotesOL,
  title={Notes on Learning with Irrelevant Attributes in the PAC Model},
  author={Aditi Dhagat and L. Hellerstein},
  year={1994}
}
In these notes, we sketch some of our work on learning with irrelevant attributes in Valiant’s PAC model [V84]. In the PAC model, the goal of the learner is to produce an approximately correct hypothesis from random sample data. If the number of relevant attributes in the target function is small, it may he desirable to produce a hypothesis that also depends on only a small number of variables. Our work is theoretical, but has real-life analogues. For example, suppose we are trying to determine… Expand

References

SHOWING 1-10 OF 12 REFERENCES
Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework
  • D. Haussler
  • Mathematics, Computer Science
  • Artif. Intell.
  • 1988
  • 554
  • PDF
A theory of the learnable
  • L. Valiant
  • Mathematics, Computer Science
  • STOC '84
  • 1984
  • 3,689
  • PDF
Learning decision lists
  • R. Rivest
  • Computer Science
  • Machine Learning
  • 1987
  • 510
  • PDF
Computational limitations on learning from examples
  • 558
  • PDF
An Introduction to Computational Learning Theory
  • 1,671
Approximation Algorithms for Combinatorial Problems
  • D. Johnson
  • Computer Science, Mathematics
  • J. Comput. Syst. Sci.
  • 1974
  • 2,398
  • PDF
On the hardness of approximating minimization problems
  • 663
  • PDF
On the ratio of optimal integral and fractional covers
  • L. Lovász
  • Computer Science, Mathematics
  • Discret. Math.
  • 1975
  • 1,122
Introduction to Computational Learning
  • 1994
Computational imitations from learning from examples
  • Journal of the ACM
  • 1993
...
1
2
...