Malicious Omissions and Errors in Answers to Membership Queries

We consider two issues in polynomial-time exact learning of concepts using membership and equivalence queries: (1) errors or omissions in answers to membership queries, and (2) learning finite variants of concepts drawn from a learnable class.To study (1), we introduce two new kinds of membership queries: limited membership queries and malicious membership queries. Each is allowed to give incorrect responses on a maliciously chosen set of strings in the domain. Instead of answering correctly about a string, a limited membership query may give a special I don't know answer, while a malicious membership query may give the wrong answer. A new parameter Lis used to bound the length of an encoding of the set of strings that receive such incorrect answers. Equivalence queries are answered correctly, and learning algorithms are allowed time polynomial in the usual parameters and L. Any class of concepts learnable in polynomial time using equivalence and malicious membership queries is learnable in polynomial time using equivalence and limited membership queries; the converse is an open problem. For the classes of monotone monomials and monotone k-term DNF formulas, we present polynomial-time learning algorithms using limited membership queries alone. We present polynomial-time learning algorithms for the class of monotone DNF formulas using equivalence and limited membership queries, and using equivalence and malicious membership queries.To study (2), we consider classes of concepts that are polynomially closed under finite exceptions and a natural operation to add exception tables to a class of concepts. Applying this operation, we obtain the class of monotone DNF formulas with finite exceptions. We give a polynomial-time algorithm to learn the class of monotone DNF formulas with finite exceptions using equivalence and membership queries. We also give a general transformation showing that any class of concepts that is polynomially closed under finite exceptions and is learnable in polynomial time using standard membership and equivalence queries is also polynomial-time learnable using malicious membership and equivalence queries. Corollaries include the polynomial-time learnability of the following classes using malicious membership and equivalence queries: deterministic finite acceptors, boolean decision trees, and monotone DNF formulas with finite exceptions.     

Theory Revision with Queries: DNF Formulas

The theory revision, or concept revision, problem is to correct a given, roughly correct concept. This problem is considered here in the model of learning with equivalence and membership queries. A revision algorithm is considered efficient if the number of queries it makes is polynomial in the revision distance between the initial theory and the target theory, and polylogarithmic in the number of variables and the size of the initial theory. The revision distance is the minimal number of syntactic revision operations, such as the deletion or addition of literals, needed to obtain the target theory from the initial theory. Efficient revision algorithms are given for three classes of disjunctive normal form expressions: monotone k-DNF, monotone m-term DNF and unate two-term DNF. A negative result shows that some monotone DNF formulas are hard to revise.     

Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle

We introduce a new fault-tolerant model of algorithmic learning using an equivalence oracle and anincomplete membership oracle, in which the answers to a random subset of the learner's membership queries may be missing. We demonstrate that, with high probability, it is still possible to learn monotone DNF formulas in polynomial time, provided that the fraction of missing answers is bounded by some constant less than one. Even when half the membership queries are expected to yield no information, our algorithm will exactly identifym-term,n-variable monotone DNF formulas with an expectedO(mn ²) queries. The same task has been shown to require exponential time using equivalence queries alone. We extend the algorithm to handle some one-sided errors, and discuss several other possible error models. It is hoped that this work may lead to a better understanding of the power of membership queries and the effects of faulty teachers on query models of concept learning.     

Exact learning of DNF formulas using DNF hypotheses

We show the following: (a) For any ε>0, log^(3+ε)n-term DNF cannot be polynomial-query learned with membership and strongly proper equivalence queries. (b) For sufficiently large t, t-term DNF formulas cannot be polynomial-query learned with membership and equivalence queries that use t^1+ε-term DNF formulas as hypotheses, for some ε<1 (c) Read-thrice DNF formulas are not polynomial-query learnable with membership and proper equivalence queries. (d) logn-term DNF formulas can be polynomial-query learned with membership and proper equivalence queries. (This complements a result of Bshouty, Goldman, Hancock, and Matar that -term DNF can be so learned in polynomial time.)Versions of (a)-(c) were known previously, but the previous versions applied to polynomial-time learning and used complexity theoretic assumptions. In contrast, (a)-(c) apply to polynomial-query learning, imply the results for polynomial-time learning, and do not use any complexity-theoretic assumptions.     

How Many Missing Answers Can Be Tolerated by Query Learners?

We consider the model of exact learning using an equivalence oracle and an incomplete membership oracle. In this model a random subset of the learners membership queries is left unanswered. Our results are as follows. First, we analyze the obvious method for coping with missing answers: search exhaustively through all possible answer patterns associated with the unanswered queries. Thereafter, we present two specific concept classes that are efficiently learnable using an equivalence oracle and a (completely reliable) membership oracle, but are provably not polynomially learnable if the membership oracle becomes slightly incomplete. The first class demonstrates that the aforementioned method of exhaustively searching through all possible answer patterns cannot be substantially improved in general (despite its apparent simplicity). The second class demonstrates that the incomplete membership oracle can be rendered useless even if it leaves only a fraction 1/poly(n) of all queries unanswered. Finally, we present a learning algorithm for monotone DNF formulas that can cope with a relatively large fraction of missing answers (more than 60%), but is as efficient (in terms of run-time and number of queries) as the classical algorithm whose questions are always answered reliably.     

Learning a subclass of k-quasi-Horn formulas with membership queries

Boolean formulas have been widely studied in the field of learning theory. We focus on the model of learning with queries, and study a restriction of the class of k-quasi-Horn formulas, that is, conjunctive normal form formulas where the number of unnegated literals per clause is at most k. This class is known to be as hard to learn as the general class CNF of conjunctive normal form formulas. By imposing some constraints, we define a fragment of this logic that can be learned using only membership queries. Also we prove that none of these constraints makes by itself the class learnable.     

Polynomial certificates for propositional classes

This paper studies the complexity of learning classes of expressions in propositional logic from equivalence queries and membership queries. In particular, we focus on bounding the number of queries that are required to learn the class ignoring computational complexity. This quantity is known to be captured by a combinatorial measure of concept classes known as the certificate complexity. The paper gives new constructions of polynomial size certificates for monotone expressions in conjunctive normal form (CNF), for unate CNF functions where each variable affects the function either positively or negatively but not both ways, and for Horn CNF functions. Lower bounds on certificate size for these classes are derived showing that for some parameter settings the new certificate constructions are optimal. Finally, the paper gives an exponential lower bound on the certificate size for a natural generalization of these classes known as renamable Horn CNF functions, thus implying that the class is not learnable from a polynomial number of queries.     

Complexity theoretic hardness results for query learning

We investigate the complexity of learning for the well-studied model in which the learning algorithm may ask membership and equivalence queries. While complexity theoretic techniques have previously been used to prove hardness results in various learning models, these techniques typically are not strong enough to use when a learning algorithm may make membership queries. We develop a general technique for proving hardness results for learning with membership and equivalence queries (and for more general query models). We apply the technique to show that, assuming , no polynomial-time membership and (proper) equivalence query algorithms exist for exactly learning read-thrice DNF formulas, unions of halfspaces over the Boolean domain, or some other related classes. Our hardness results are representation dependent, and do not preclude the existence of representation independent algorithms.?The general technique introduces the representation problem for a class F of representations (e.g., formulas), which is naturally associated with the learning problem for F. This problem is related to the structural question of how to characterize functions representable by formulas in F, and is a generalization of standard complexity problems such as Satisfiability. While in general the representation problem is in , we present a theorem demonstrating that for "reasonable" classes F, the existence of a polynomial-time membership and equivalence query algorithm for exactly learning F implies that the representation problem for F is in fact in co-NP. The theorem is applied to prove hardness results such as the ones mentioned above, by showing that the representation problem for specific classes of formulas is NP-hard. Received: December 6, 1994     

Resource-Bounded Measure and Learnability

We consider the resource-bounded measure of polynomial-time learnable subclasses of polynomial-size circuits. We show that if EXP ≠ MA, then every PAC-learnable subclass of P/poly has EXP-measure zero. We introduce a nonuniformly computable variant of resource-bounded measure and show that, for every fixed polynomial q , any polynomial-time learnable subclass of circuits of size q has measure zero with respect to P/poly. We relate our results to the question of whether the class of Boolean circuits is polynomial-time learnable. Received July 15, 1998, and in final form September 9, 1999.     

Simple learning algorithms using divide and conquer

This paper investigates what happens when a learning algorithm for a classC attempts to learn target formulas from a different class. In many cases, the learning algorithm will find a bad attribute or a property of the target formula which precludes its membership in the classC. To continue the learning process, we proceed by building a decision tree according to the possible values of this attribute (divide) and recursively run the learning algorithm for each value (conquer). This paper shows how to recursively run the learning algorithm for each value using the oracles of the target.We demonstrate that the application of this idea on some known learning algorithms can both simplify the algorithm and provide additional power to learn more classes. In particular, we give a simple exact learning algorithm, using membership and equivalence queries, for the class of DNF that is almost unate, that is, unate with the addition ofO (logn) nonunate variables and a constant number of terms. We also find algorithms in different models for boolean functions that depend onk terms.     

Proper Learning Algorithm for Functions of k Terms under Smooth Distributions

In this paper, we introduce a probabilistic distribution, called a smooth distribution, which is a generalization of variants of the uniform distribution such as q-bounded distribution and product distribution. Then, we give an algorithm that, under the smooth distribution, properly learns the class of functions of k terms given as _k ^k_n={g(f₁(v), …, f_k(v)) | g _k, f₁, …, f_{k n}} in polynomial time for constant k, where _k is the class of all Boolean functions of k variables and _n is the class of terms over n variables. Although class _k ^k_n was shown by Blum and Singh to be learned using DNF as the hypothesis class, it has remained open whether it is properly learnable under a distribution-free setting.     

Learning Read-Constant Polynomials of Constant Degree Modulo Composites

Boolean functions that have constant degree polynomial representation over a fixed finite ring form a natural and strict subclass of the complexity class ACC⁰. They are also precisely the functions computable efficiently by programs over fixed and finite nilpotent groups. This class is not known to be learnable in any reasonable learning model. In this paper, we provide a deterministic polynomial time algorithm for learning Boolean functions represented by polynomials of constant degree over arbitrary finite rings from membership queries, with the additional constraint that each variable in the target polynomial appears in a constant number of monomials. Our algorithm extends to superconstant but low degree polynomials and still runs in quasipolynomial time.     

Learning two-tape automata from queries and counterexamples

We investigate the learning problem of two-tape deterministic finite automata (2-tape DFAs) from queries and counterexamples. Instead of accepting a subset of ∑*, a 2-tape DFA over an alphabet ∑ accepts a subset of ∑* × ∑*, and therefore, it can specify a binary relation on ∑*. In [3] Angluin showed that the class of deterministic finite automata (DFAs) is learnable in polynomial time from membership queries and equivalence queries, namely, from a minimally adequate teacher (MAT). In this article we show that the class of 2-tape DFAs is learnable in polynomial time from MAT. More specifically, we show an algorithm that, given any languageL accepted by an unknown 2-tape DFAM, learns from MAT a two-tape nonde-terministic finite automaton (2-tape NFA)M′ acceptingL in time polynomial inn andl, wheren is the size ofM andl is the maximum length of any counterexample provided during the learning process. This work was supported in part by Grants-in-Aid for Scientific Research No. 04229105 from the Ministry of Education, Science, and Culture, Japan.     

Learning with errors in answers to membership queries

We study the learning models defined in [D. Angluin, M. Krikis, R.H. Sloan, G. Turán, Malicious omissions and errors in answering to membership queries, Machine Learning 28 (2–3) (1997) 211–255]: Learning with equivalence and limited membership queries and learning with equivalence and malicious membership queries.We show that if a class of concepts that is closed under projection is learnable in polynomial time using equivalence and (standard) membership queries then it is learnable in polynomial time in the above models. This closes the open problems in [D. Angluin, M. Krikis, R.H. Sloan, G. Turán, Malicious omissions and errors in answering to membership queries, Machine Learning 28 (2–3) (1997) 211–255].Our algorithm can also handle errors in the equivalence queries.     

On the Limits of Proper Learnability of Subclasses of DNF Formulas

Bshouty, Goldman, Hancock and Matar have shown that up to term DNF formulas can be properly learned in the exact model with equivalence and membership queries. Given standard complexity-theoretical assumptions, we show that this positive result for proper learning cannot be significantly improved in the exact model or the PAC model extended to allow membership queries. Our negative results are derived from two general techniques for proving such results in the exact model and the extended PAC model. As a further application of these techniques, we consider read-thrice DNF formulas. Here we improve on Aizenstein, Hellerstein, and Pitt's negative result for proper learning in the exact model in two ways. First, we show that their assumption of NP co-NP can be replaced with the weaker assumption of P NP. Second, we show that read-thrice DNF formulas are not properly learnable in the extended PAC model, assuming RP NP.     

The query complexity of learning DFA

It is known that the class of deterministic finite automata is polynomial time learnable by using membership and equivalence queries. We investigate the query complexity of learning deterministic finite automata, i.e., the number of membership and equivalence queries made during the process of learning. We extend a known lower bound on membership queries to the case of randomized learning algorithms, and prove lower bounds on the number of alternations between membership and equivalence queries. We also show that a trade-off exists, allowing us to reduce the number of equivalence queries at the price of increasing the number of membership queries.     

DNA-based algorithms for learning Boolean formulae

We apply a DNA-based massively parallel exhaustive search to solving the computational learning problems of DNF (disjunctive normal form) Boolean formulae. Learning DNF formulae from examples is one of the most important open problems in computational learning theory and the problem of learning 3-term DNF formulae is known as intractable if RP NP. We propose new methods to encode any k-term DNF formula to a DNA strand, evaluate the encoded DNF formula for a truth-value assignment by using hybridization and primer extension with DNA polymerase, and find a consistent DNF formula with the given examples. By employing these methods, we show that the class of k-term DNF formulae (for any constant k) and the class of general DNF formulae are efficiently learnable on DNA computer.Second, in order for the DNA-based learning algorithm to be robust for errors in the data, we implement the weighted majority algorithm on DNA computers, called DNA-based majority algorithm via amplification (DNAMA), which take a strategy of ``amplifying' the consistent (correct) DNA strands. We show a theoretical analysis for the mistake bound of the DNA-based majority algorithm via amplification, and imply that the amplification to ``double the volumes' of the correct DNA strands in the test tube works well.