COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
GroupLens: an open architecture for collaborative filtering of netnews
CSCW '94 Proceedings of the 1994 ACM conference on Computer supported cooperative work
Generalized teaching dimensions and the query complexity of learning
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Oracles and queries that are sufficient for exact learning
Journal of Computer and System Sciences
How many queries are needed to learn?
Journal of the ACM (JACM)
Communications of the ACM
Malicious Omissions and Errors in Answers to Membership Queries
Machine Learning
Approximate nearest neighbors: towards removing the curse of dimensionality
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Efficient search for approximate nearest neighbor in high dimensional spaces
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
A threshold of ln n for approximating set cover
Journal of the ACM (JACM)
An optimal algorithm for approximate nearest neighbor searching
SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms
Machine Learning
Machine Learning
Collaborative Filtering Using Weighted Majority Prediction Algorithms
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Quantum versus Classical Learnability
CCC '01 Proceedings of the 16th Annual Conference on Computational Complexity
Empirical analysis of predictive algorithms for collaborative filtering
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
A general dimension for query learning
Journal of Computer and System Sciences
Hi-index | 0.00 |
We consider the problem of determining which of a set of experts has tastes most similar to a given user by asking the user questions about his likes and dislikes. We describe a simple algorithm for generating queries for a theoretical model of this problem. We show that the algorithm requires at most opt(F)(ln(|F|/opt(F)) + 1) + 1 queries to find the correct expert, where opt(F) is the optimal worst-case bound on the number of queries for learning arbitrary elements of the set of experts F. The algorithm runs in time polynomial in |F| and |X| (where X is the domain) and we prove that no polynomial-time algorithm can have a significantly better bound on the number of queries unless all problems in NP have nO(log log n) time algorithms. We also study a more general case where the user ratings come from a finite set Y and there is an integer-valued loss function ℓ on Y that is used to measure the distance between the ratings. Assuming that the loss function is a metric and that there is an expert within a distance η from the user, we give a polynomial-time algorithm that is guaranteed to find such an expert after at most 2opt(F, η) ln \frac{|F|}{1+\newdeg(F,\eta)} + 2(η + 1)(1 + deg(F, η)) queries, where deg(F, η) is the largest number of experts in F that are within a distance 2η of any f ∈ F.