|
| This Article | ||
| | ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
33rd Annual Symposium on Foundations of Computer Science (FOCS 1992)
Pittsburgh, PA, USA
October 24-October 27
ISBN: 0-8186-2900-2
| ASCII Text | x | ||
| H. Aizenstein, L. Hellerstein, L. Pitt, "Read-thrice DNF is hard to learn with membership and equivalence queries," Foundations of Computer Science, IEEE Annual Symposium on, pp. 523-532, 33rd Annual Symposium on Foundations of Computer Science (FOCS 1992), 1992. | |||
| BibTex | x | ||
| @article{ 10.1109/SFCS.1992.267799, author = {H. Aizenstein and L. Hellerstein and L. Pitt}, title = {Read-thrice DNF is hard to learn with membership and equivalence queries}, journal ={Foundations of Computer Science, IEEE Annual Symposium on}, volume = {0}, year = {1992}, isbn = {0-8186-2900-2}, pages = {523-532}, doi = {http://doi.ieeecomputersociety.org/10.1109/SFCS.1992.267799}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Foundations of Computer Science, IEEE Annual Symposium on TI - Read-thrice DNF is hard to learn with membership and equivalence queries SN - 0-8186-2900-2 SP523 EP532 A1 - H. Aizenstein, A1 - L. Hellerstein, A1 - L. Pitt, PY - 1992 KW - disjunctive normal KW - membership KW - equivalence queries KW - nonlearnability KW - exact learning KW - polynomial-time membership KW - read-thrice DNF formulas KW - boolean formulas VL - 0 JA - Foundations of Computer Science, IEEE Annual Symposium on ER - | |||
A general technique is developed to obtain nonlearnability results in the model of exact learning from equivalence and membership queries. The technique is applied to show that, assuming NP not=co-NP, there does not exist a polynomial-time membership and equivalence query algorithm for exactly learning read-thrice DNF formulas-boolean formulas in disjunctive normal form where each variable appears at most three times. This result adds evidence to the conjecture that DNF is hard to learn in the membership and equivalence query model.
Index Terms:
disjunctive normal, membership, equivalence queries, nonlearnability, exact learning, polynomial-time membership, read-thrice DNF formulas, boolean formulas
Citation:
H. Aizenstein, L. Hellerstein, L. Pitt, "Read-thrice DNF is hard to learn with membership and equivalence queries," focs, pp.523-532, 33rd Annual Symposium on Foundations of Computer Science (FOCS 1992), 1992
Usage of this product signifies your acceptance of the Terms of Use.