Learning DNF in Time
نویسندگان
چکیده
"! # %$'&# )(+* ,.-0/ 213* # 4 ! 5, * 687 9 : ! ,29; !<1= >1 86 ?5@ 5* -BADCDEF,=GH 5*JI:G 13* %13K / L 213 >K ,.-NM#&# 2OPK86P1QM , / 6R #,
منابع مشابه
A Subexponential Exact Learning Algorithm for DNF Using Equivalence Queries
We present a 2 ~ O(p 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 rst subexponential time PAC-learning algorithm for DNF under any distribution.
متن کاملTight Bounds on Proper Equivalence Query Learning of DNF
We prove a new structural lemma for partial Boolean functions f , which we call the seed lemma for DNF. Using the lemma, we give the first subexponential algorithm for proper learning of poly(n)-term DNF in Angluin’s Equivalence Query (EQ) model. The algorithm has time and query complexity 2 √ , which is optimal. We also give a new result on certificates for DNF-size, a simple algorithm for pro...
متن کاملNew Results for Random Walk Learning
In a very strong positive result for passive learning algorithms, Bshouty et al. showed that DNF expressions are efficiently learnable in the uniform random walk model. It is natural to ask whether the more expressive class of thresholds of parities (TOP) can also be learned efficiently in this model, since both DNF and TOP are efficiently uniform-learnable from queries. However, the time bound...
متن کاملAttribute-Efficient and Non-adaptive Learning of Parities and DNF Expressions
We consider the problems of attribute-efficient PAC learning of two well-studied concept classes: parity functions and DNF expressions over {0,1}n. We show that attribute-efficient learning of parities with respect to the uniform distribution is equivalent to decoding high-rate random linear codes from low number of errors, a long-standing open problem in coding theory. This is the first eviden...
متن کاملLearning DNF by Approximating Inclusion-Exclusion Formulae
Probably Approximately Correct learning algorithms generalize a small number of examples about an unknown concept into a function that can predict a future observation. More formally, let X and Y be the instance and outcome spaces, respectively. Then a PAC algorithm observes randomly drawn examples (x; f(x)) about an unknown concept f : X ! Y . These examples are independently and identically d...
متن کاملMansour's Conjecture is True for Random DNF Formulas
In 1994, Y. Mansour conjectured that for every DNF formula on n variables with t terms there exists a polynomial p with t non-zero coefficients such that Ex∈{0,1} [(p(x) − f(x))] ≤ ǫ. We make the first progress on this conjecture and show that it is true for randomly chosen DNF formulas and read-once DNF formulas. Our result yields the first polynomial-time query algorithm for agnostically lear...
متن کامل