Lower Bounds for the Complexity of Learning Half-Spaces with Membership Queries
نویسندگان
چکیده
Exact learning of half-spaces over finite subsets of IR from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from all the other ones of the concept class under consideration. For a domain consisting of all integer points of some polytope we give non-trivial lower bounds on the complexity of exact identification of half-spaces. These bounds are near to known upper bounds.
منابع مشابه
A general dimension for query learning
We introduce a combinatorial dimension that characterizes the number of queries needed to exactly (or approximately) learn concept classes in various models. Our general dimension provides tight upper and lower bounds on the query complexity for all sorts of queries, not only for example-based queries as in previous works. As an application we show that for learning DNF formulas, unspecified at...
متن کاملEfficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circuit class C in Angluin’s model of exact learning from membership and equivalence queries or in Valiant’s PAC model yields a lower bound against C. More specifically, we prove that any subexponential time, determinstic ex...
متن کاملA Guide to Learning Arithmetic Circuits
An arithmetic circuit is a directed acyclic graph in which the operations are {+,×}. In this paper, we exhibit several connections between learning algorithms for arithmetic circuits and other problems. In particular, we show that: • Efficient learning algorithms for arithmetic circuit classes imply explicit exponential lower bounds. • General circuits and formulas can be learned efficiently wi...
متن کاملTwo Equivalent Presentations for the Norm of Weighted Spaces of Holomorphic Functions on the Upper Half-plane
Introduction In this paper, we intend to show that without any certain growth condition on the weight function, we always able to present a weighted sup-norm on the upper half plane in terms of weighted sup-norm on the unit disc and supremum of holomorphic functions on the certain lines in the upper half plane. Material and methods We use a certain transform between the unit dick and the uppe...
متن کاملLearnability of Kolmogorov - Easy
Circuit expressions were introduced to provide a natural link between Computational Learning and certain aspects of Structural Complexity. Upper and lower bounds on the learnability of circuit expressions are known. We study here the case in which the circuit expressions are of low (time-bounded) Kolmogorov complexity. We show that these are polynomial-time learnable from membership queries in ...
متن کامل