Exact learning from an honest teacher that answers membership queries

Bshouty, Nader H.

doi:10.1016/j.tcs.2018.04.034

Cited by 12 publications

(10 citation statements)

References 263 publications

(435 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the following, we give a brief summary of some of the known results of the learnability of the class DT d . In [13,18], it is shown that 1 :…”

Section: Known Resultsmentioning

confidence: 99%

“…Vitaly Feldman [19] introduced the first randomized non-adaptive algorithm that finds the heavy Fourier coefficients. Applying his algorithm to the class DT d gives a non-adaptive learning algorithm with query complexity Õ(2 2d ) log 2 n. See [18] for the algorithm. Applying the reduction from [13] to the algorithm of Feldman gives a non-adaptive learning algorithm with query complexity Õ(2 2d ) log n. We want to draw the reader's attention that any result for the non-adaptive case implies the same result for the adaptive case.…”

Section: Randomized Complexitymentioning

confidence: 99%

See 1 more Smart Citation

Exact learning of juntas from membership queries

Bshouty

Costa

2018

Theoretical Computer Science

Self Cite

View full text Add to dashboard Cite

In this paper we study adaptive and non-adaptive exact learning of Juntas from membership queries. We use new techniques to find new bounds, narrow some of the gaps between the lower bounds and upper bounds and find new deterministic and randomized algorithms with small query and time complexities.Some of the bounds are tight in the sense that finding better ones either gives a breakthrough result in some long-standing combinatorial open problem or needs a new technique that is beyond the existing ones.

show abstract

“…In the following, we give a brief summary of some of the known results of the learnability of the class DT d . In [13,18], it is shown that 1 :…”

Section: Known Resultsmentioning

confidence: 99%

Section: Randomized Complexitymentioning

confidence: 99%

Exact learning of juntas from membership queries

Bshouty

Costa

2018

Theoretical Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Concept learning via queries has been widely studied in the theoretical machine learning literature. There are wellknown results for several classes of concepts [21,20], e.g. conjunctions of Horn clauses [5], k-term DNF [17] (or CNF) formula, decision trees [19] etc.…”

Section: Related Workmentioning

confidence: 99%

“…Active constraint acquisition is a special case of query-directed learning, also known as exact learning [19,20]. Concept learning via queries has been widely studied in the theoretical machine learning literature.…”

Section: Related Workmentioning

confidence: 99%

Efficient multiple constraint acquisition

Tsouros

Stergiou

2020

Constraints

View full text Add to dashboard Cite

Constraint acquisition systems such as QuAcq and MultiAcq can assist non-expert users to model their problems as constraint networks by classifying (partial) examples as positive or negative. For each negative example, the former focuses on one constraint of the target network, while the latter can learn a maximum number of constraints. Two bottlenecks of the acquisition process where both these algorithms encounter problems are the large number of queries required to reach convergence, and the high cpu times needed to generate queries, especially near convergence.In this paper we propose algorithmic and heuristic methods to deal with both these issues. We first describe an algorithm, called MQuAcq, that blends the main idea of MultiAcq into QuAcq resulting in a method that learns as many constraints as MultiAcq does after a negative example, but with a lower complexity. A detailed theoretical analysis of the proposed algorithm is also presented. Then we turn our attention to query generation which is a significant but rather overlooked part of the acquisition process. We describe how query generation in a typical constraint acquisition system operates, and we propose heuristics for improving its efficiency. Experiments from various domains demonstrate that our resulting algorithm that integrates all the new techniques does not only generate considerably fewer queries than QuAcq and MultiAcq, but it is also by far faster than both of them, in average query generation time as well as in total run time, and also largely alleviates the premature convergence problem.

show abstract

“…Active or interactive constraint acquisition systems interact with the user while learning the constraint network. This is a special case of query-directed learning, also known as "exact learning" [11,10]. State-of-the-art constraint acquisition algorithms like QuAcq [5], MQuAcq [20] and MQuAcq-2 [19] use the version space learning method [18], extended for learning constraint networks.…”

Section: Introductionmentioning

confidence: 99%

Omissions in Constraint Acquisition

Tsouros

Stergiou

Bessière

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Interactive constraint acquisition is a special case of query-directed learning, also known as "exact" learning. It is used to assist non-expert users in modeling a constraint problem automatically by posting examples to the user that have to be classified as solutions or non-solutions. One significant issue that has not been addressed in the literature of constraint acquisition is the possible presence of uncertainty in the answers of the users. We address this by introducing Limited Membership Queries, where the user has the option of replying "I don't know", corresponding to "omissions" in exact learning. We present two algorithms for handling omissions. The first one deals with omissions that are independent events, while the second assumes that omissions are related to gaps in the user's knowledge. We present theoretical results about both methods and we evaluate them on benchmark problems. Importantly, our second algorithm can not only learn (a part of) the target network, but also the constraints that cause the user's uncertainty.

show abstract

Exact learning from an honest teacher that answers membership queries

Cited by 12 publications

References 263 publications

Exact learning of juntas from membership queries

Exact learning of juntas from membership queries

Efficient multiple constraint acquisition

Omissions in Constraint Acquisition

Contact Info

Product

Resources

About