Computer Science – Learning
Scientific paper
2011-07-11
Extended version of COLT 2009 Paper
Computer Science
Learning
Scientific paper
In the supervised learning setting termed Multiple-Instance Learning (MIL), the examples are bags of instances, and the bag label is a function of the labels of its instances. Typically, this function is the Boolean OR. The learner observes a sample of bags and the bag labels, but not the instance labels that determine the bag labels. The learner is then required to emit a classification rule for bags based on the sample. MIL has numerous applications, and many heuristic algorithms have been used successfully on this problem, each adapted to specific settings or applications. In this work we provide a unified theoretical analysis for MIL, which holds for any underlying hypothesis class, regardless of a specific application or problem domain. We show that the sample complexity of MIL is only poly-logarithmically dependent on the size of the bag, for any underlying hypothesis class. In addition, we introduce a new PAC-learning algorithm for MIL, which employs a regular supervised learning algorithm as an oracle. We prove that efficient PAC-learning for MIL can be generated from any efficient non-MIL supervised learning algorithm that handles one-sided error. The computational complexity of the resulting algorithm is only polynomially dependent on the bag size.
Sabato Sivan
Tishby Naftali
No associations
LandOfFree
Multi-Instance Learning with Any Hypothesis Class does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Multi-Instance Learning with Any Hypothesis Class, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-Instance Learning with Any Hypothesis Class will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-137771