Polynomial Learnability of Stochastic Rules with Respect to the KL-Divergence and Quadratic Distance

@inproceedings{Abe2001PolynomialLO,
  title={Polynomial Learnability of Stochastic Rules with Respect to the KL-Divergence and Quadratic Distance},
  author={Naoki Abe and J. Takeuchi and Manfred K. Warmuth},
  year={2001}
}
We consider the problem of efficient learning of probabilistic concepts (p-concepts) and more generally stochastic rules in the sense defined by Kearns and Schapire [6] and by Yamanishi [18]. Their models extend the PAC-learning model of Valiant [16] to the learning scenario in which the target concept or function is stochastic rather than deterministic as in Valiant’s original model. In this paper, we consider the learnability of stochastic rules with respect to the classic ‘Kullback-Leibler… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 15 REFERENCES

Empirical Processes: Theory and Applications

  • D. Pollard
  • Institute of Mathematical Statistics and American…
  • 1990
Highly Influential
7 Excerpts

The gradient projection method for nonlinear programming. part i. linear constraints

  • J. B. Rosen
  • J. S.I.A.M., vol.8, no.1, pp.181–217, .
  • 1960
Highly Influential
1 Excerpt

Similar Papers

Loading similar papers…