On parallel attribute-efficient learning
TLDR
It is proved that any strategy that uses an optimal query number needs Θ(r) rounds in the worst case, and several strategies are obtained which use a constant number of rounds, O(2rpoly(r log n)) queries, and only 2O( r)n poly(log n) computations.About:
This article is published in Journal of Computer and System Sciences.The article was published on 2003-08-01 and is currently open access. It has received 14 citations till now. The article focuses on the topics: Boolean function & Monotone polygon.read more
Citations
More filters
Book ChapterDOI
Threshold group testing
TL;DR: It is shown that the p positive elements can be determined up to a constant number of misclassifications, bounded by the gap between the thresholds, and the number of tests needed to achieve this goal if n elements are given.
Journal ArticleDOI
Competitive group testing and learning hidden vertex covers with minimum adaptivity
TL;DR: This work explores group testing strategies that use a nearly optimal number of pools and a few stages although d is not known beforehand, and provides a classification of types of randomized search strategies in general.
Journal ArticleDOI
Threshold Group Testing
TL;DR: It is shown that the p positive elements can be determined up to a constant number of misclassifications, bounded by the gap between the thresholds, and a two-phase strategy consisting of a Distill and a Compress phase is proposed.
Journal ArticleDOI
Exact learning from an honest teacher that answers membership queries
TL;DR: In this paper, the authors present some of the results known from the literature, different techniques used, some new problems, and open problems for the problem of finding a minimum number of queries, optimal time complexity, and optimal resources.
Book ChapterDOI
Exact Learning from Membership Queries: Some Techniques, Results and New Directions
TL;DR: The goal is to exactly find exactly learn f with minimum number of queries and optimal time complexity, different techniques used mainly for the problem of exact learning and new directions that are worth investigating.
References
More filters
Journal ArticleDOI
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm
TL;DR: This work presents one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions.
Journal ArticleDOI
Binary codes with specified minimum distance
TL;DR: New results are given in the field in the form of theorems which permit systematic construction of codes for given n, d ; for some n,d , the codes contain the greatest possible numbers of points.
Book ChapterDOI
A Comparative Survey of Non-Adaptive Pooling Designs
TL;DR: A chronology of key events and figures from the year in the history of the United States, as well as some of the individuals and institutions that were involved in the manufacture and distribution of goods and services, are recalled.
Journal ArticleDOI
Learning in the Presence of Finitely or Infinitely Many Irrelevant Attributes
TL;DR: The problem of learning boolean functions in query and mistake-bound models in the presence of irrelevant attributes is addressed and a large class of functions, including the set of monotone functions, is described, for which learnability does imply attribute-efficient learnability in this model.
Proceedings ArticleDOI
Lower bounds for identifying subset members with subset queries
TL;DR: In this paper, it was shown that for general group testing algorithms, if the average number of queries over the course of $n^\gamma$ ($gamma>0$) independent experiments is O(n^{1-πsilon}), then with high probability the non-singleton subsets are queried.