Communications of the ACM
Cryptographic hardness of distribution-specific learning
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Predicate migration: optimizing queries with expensive predicates
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Randomized algorithms
On chromatic sums and distributed resource allocation
Information and Computation
Query strategies for priced information (extended abstract)
STOC '00 Proceedings of the thirty-second annual ACM symposium on Theory of computing
Optimal Information Gathering on the Internet with Time and Cost Constraints
SIAM Journal on Computing
Approximating Min-sum Set Cover
APPROX '02 Proceedings of the 5th International Workshop on Approximation Algorithms for Combinatorial Optimization
Efficient information gathering on the Internet
FOCS '96 Proceedings of the 37th Annual Symposium on Foundations of Computer Science
Adaptive ordering of pipelined stream filters
SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
Budgeted learning of nailve-bayes classifiers
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
The pipelined set cover problem
ICDT'05 Proceedings of the 10th international conference on Database Theory
On the competitive ratio of evaluating priced functions
SODA '06 Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm
Flow algorithms for two pipelined filter ordering problems
Proceedings of the twenty-fifth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
The hardness of the Expected Decision Depth problem
Information Processing Letters
Foundations and Trends in Databases
A generic flow algorithm for shared filter ordering problems
Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Algorithms for distributional and adversarial pipelined filter ordering problems
ACM Transactions on Algorithms (TALG)
Proceedings of the forty-first annual ACM symposium on Theory of computing
On the competitive ratio of evaluating priced functions
Journal of the ACM (JACM)
Competitive Boolean function evaluation: Beyond monotonicity, and the symmetric case
Discrete Applied Mathematics
Paging multiple users in cellular network: yellow page and conference call problems
SEA'10 Proceedings of the 9th international conference on Experimental Algorithms
Adaptive submodularity: theory and applications in active learning and stochastic optimization
Journal of Artificial Intelligence Research
Parallel pipelined filter ordering with precedence constraints
ACM Transactions on Algorithms (TALG)
Decision-theoretic troubleshooting: Hardness of approximation
International Journal of Approximate Reasoning
Hi-index | 0.00 |
We study an extension of the "standard" learning models to settings where observing the value of an attribute has an associated cost (which might be different for different attributes). Our model assumes that the correct classification is given by some target function f from a class of functions cal F; most of our results discuss the ability to learn a clause (an OR function of a subset of the variables) in various settings:Offline: We are given both the function f and the distribution D that is used to generate an input x. The goal is to design a strategy to decide what attribute of x to observe next so as to minimize the expected evaluation cost of f(x). (In this setting there is no "learning" to be done but only an optimization problem to be solved; this problem to be NP-hard and hence approximation algorithms are presented.)Distributional online: We study two types of "learning" problems; one where the target function f is known to the learner but the distribution D is unknown (and the goal is to minimize the expected cost including the cost that stems from "learning" D), and the other where f is unknown (except that f∈cal F) but D is known (and the goal is to minimize the expected cost while limiting the prediction error involved in "learning" f).Adversarial online: We are given f, however the inputs are selected adversarially. The goal is to compare the learner's cost to that of the best fixed evaluation order (i.e., we analyze the learner's performance by a competitive analysis).