Efficient noise-tolerant learning from statistical queries
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Solving the multiple instance problem with axis-parallel rectangles
Artificial Intelligence
Approximating hyper-rectangles: learning and pseudo-random sets
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Machine Learning - Special issue on the ninth annual conference on computational theory (COLT '96)
A Note on Learning from Multiple-Instance Examples
Machine Learning - Special issue on the ninth annual conference on computational theory (COLT '96)
Multiple-Instance Learning of Real-Valued Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Multiple-Instance Learning for Natural Scene Classification
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Solving the Multiple-Instance Problem: A Lazy Learning Approach
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Multiple-Instance Learning of Real-Valued Geometric Patterns
Annals of Mathematics and Artificial Intelligence
Learning from ambiguity
Multiple-instance image database retrieval by spatial similarity based on Interval Neighbor Group
Proceedings of the ACM International Conference on Image and Video Retrieval
Hi-index | 0.00 |
While there has been a significant amount of theoretical and empirical research on the multiple-instance learning model, most of this research is for concept learning. However, for the important application area of drug discovery, a real-valued classification is preferable. In this paper we initiate a theoretical study of real-valued multiple-instance learning. We prove that the problem of finding a target point consistent with a set of labeled multiple-instance examples (or bags) is NP-complete, and that the problem of learning from real-valued multiple-instance examples is as hard as learning DNF. Another contribution of our work is in defining and studying a multiple-instance membership query (MI-MQ). We give a positive result on exactly learning the target point for a multiple-instance problem in which the learner is provided with a MI-MQ oracle and a single adversarially selected bag.