Evaluation May Be Easier than Generation

@inproceedings{Naor1996EvaluationMB,
  title={Evaluation May Be Easier than Generation},
  author={Moni Naor},
  year={1996}
}
Kearns et al. 18] deened two notions for learning a distribution D. The rst is with generator, where the learner presents a generator that outputs a distribution identical or close to D. The other is with an evaluator, where the learner presents a procedure that on input x evaluates correctly (or approximates) the probability that x is generated by D. They showed an example where eecient learning by a generator is possible , but learning by an evaluator is computationally infeasible. Though it… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Separating distributionfree and mistakebound learning models over the Boolean domain

  • A. Blum
  • How to Sign Given Any Trapdoor Function , Proc…
  • 1988

Vazirani Matching is as easy as matrix inversion

  • U. V. Vazirani K. Mulmuley, V. V.
  • 1987

Rivest A secure digital signature scheme

  • S. Micali S. Goldwasser, R.
  • SIAM J . on Computing
  • 1986

Similar Papers

Loading similar papers…