Learning symmetric k-juntas in time n^o(k)
| dc.creator | Kolountzakis, Mihail N. | |
| dc.creator | Markakis, Evangelos | |
| dc.creator | Mehta, Aranyak | |
| dc.date | 2005-04-12 | |
| dc.date.accessioned | 2026-07-07T05:19:03Z | |
| dc.date.available | 2026-07-07T05:19:03Z | |
| dc.description | We give an algorithm for learning symmetric k-juntas (boolean functions of $n$ boolean variables which depend only on an unknown set of $k$ of these variables) in the PAC model under the uniform distribution, which runs in time n^{O(k/\log k)}. Our bound is obtained by proving the following result: Every symmetric boolean function on k variables, except for the parity and the constant functions, has a non-zero Fourier coefficient of order at least 1 and at most O(k/\log k). This improves the previously best known bound of (3/31)k, and provides the first n^{o(k)} time algorithm for learning symmetric juntas. | |
| dc.identifier | https://arxiv.org/abs/math/0504246 | |
| dc.identifier | http://arxiv.org/abs/math/0504246 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/74874 | |
| dc.subject | Combinatorics | |
| dc.title | Learning symmetric k-juntas in time n^o(k) | |
| dc.type | text |