Conjunctions of Unate DNF Formulas: Learning and Structure

نویسندگان

  • Aaron Feigelson
  • Lisa Hellerstein
چکیده

A central topic in query learning is to determine which classes of Boolean formulas are e ciently learnable with membership and equivalence queries. We consider the class Rk consisting of conjunctions of k unate DNF formulas. This class generalizes the class of k-clause CNF formulas, and the class of unate DNF formulas, both of which are known to be learnable in polynomial time with membership and equivalence queries. We prove that R2 can be properly learned with a polynomial number of polynomial-size membership and equivalence queries, but can be properly learned in polynomial time with such queries if and only if P = NP. Thus the barrier to properly learning R2 with membership and equivalence queries is computational rather than informational. Few results of this type are known. In our proofs, we use recent results of Hellerstein, Pillaipakamnatt, Raghavan, and Wilkins, characterizing the classes that are polynomial-query learnable, together with work of Bshouty on the monotone dimension of Boolean functions. We extend some of our results to Rk, and pose open questions on learning DNF formulas of small monotone dimension. We also prove structural results for Rk. We construct, for any xed k 2, a class of functions f that cannot be represented by any formula in Rk, but which cannot be \easily" shown to have this property. More precisely, for any function f on n variables in the class, the value of f on any polynomial-size set of points in its domain is not a witness that f cannot be represented by a formula in Rk. Our construction is based on BCH codes. iii Symbols used in the paper: R2 script R squared Mb1(f) script M sub (b sub 1) of e greater-than-or-equal-to oplus : neg 2 element-of subseteq equiv 1 in nity V bigwedge ^ wedge 6= not equal _ vee [ cup H delta sub H iv

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Theory revision with queries: results and problems

A brief overview is given of recent results on theory revision with queries for propositional formulas, such as monotone and unate DNF, Horn formulas, read-once formulas, and threshold functions. Several open problems are formulated for revision in propositional and predicate logic, and finite automata.

متن کامل

Complexity Theoretic Limitations on Learning DNF's

Using the recently developed framework of [14], we show that under a natural assumption on the complexity of refuting random K-SAT formulas, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of learning intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously ...

متن کامل

Decision Trees: More Theoretical Justification

We study impurity-based decision tree algorithms such as CART, C4.5, etc., so as to better understand their theoretical underpinnings. We consider such algorithms on special forms of functions and distributions. We deal with the uniform distribution and functions that can be described as unate functions, linear threshold functions and readonce DNF. For unate functions we show that that maximal ...

متن کامل

Learning 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 کامل

Efficiency versus Convergence of Boolean Kernels for On-Line Learning Algorithms

We study online learning in Boolean domains using kernels which capture feature expansions equivalent to using conjunctions over basic features. We demonstrate a tradeoff between the computational efficiency with which these kernels can be computed and the generalization ability of the resulting classifier. We first describe several kernel functions which capture either limited forms of conjunc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Inf. Comput.

دوره 140  شماره 

صفحات  -

تاریخ انتشار 1998