Computer Science – Learning
Scientific paper
2010-05-13
Computer Science
Learning
Scientific paper
We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is "similar" to a training sample, then the testing error is close to the training error. This provides a novel approach, different from the complexity or stability arguments, to study generalization of learning algorithms. We further show that a weak notion of robustness is both sufficient and necessary for generalizability, which implies that robustness is a fundamental property for learning algorithms to work.
Mannor Shie
Xu Huan
No associations
LandOfFree
Robustness and Generalization 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 Robustness and Generalization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robustness and Generalization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-640193