Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



LATEST > REPORTS:
RSS-Feedprevious PreviousNext next

TR95-061 | 27th November 1995
Alexander E. Andreev, Andrea E. F. Clementi, Jose' D. P. Rolim

Hitting sets derandomize BPP

Revisions: 1

We show that hitting sets can derandomize any BPP-algorithm.
This gives a positive answer to a fundamental open question in
probabilistic algorithms. More precisely, we present a polynomial
time deterministic algorithm which uses any given hitting set
to approximate the fractions of 1's in the ... more >>>


TR95-060 | 21st November 1995
Nader Bshouty

A Subexponential Exact Learning Algorithm for DNF Using Equivalence Queries


We present a $2^{\tilde O(\sqrt{n})}$ time exact learning
algorithm for polynomial size
DNF using equivalence queries only. In particular, DNF
is PAC-learnable in subexponential time under any distribution.
This is the first subexponential time
PAC-learning algorithm for DNF under any distribution.

more >>>

TR95-059 | 21st November 1995
Nader Bshouty

The Monotone Theory for the PAC-Model

We show that a DNF formula that has a CNF representation that contains
at least one ``$1/poly$-heavy''
clause with respect to a distribution $D$ is weakly learnable
under this distribution. So DNF that are not weakly
learnable under the distribution $D$ do not have
any ``$1/poly$-heavy'' clauses in any of ... more >>>



previous PreviousNext next


ISSN 1433-8092 | Imprint