Robustness and Generalization

,  -

Publications: arXiv Add/Edit

Abstract: Add/Edit

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.

Keywords: Add/Edit


Code Links

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

K-Support norm based adversarial training

0

Languages: Scala Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Stylometry classifier

0

Languages: Python Add/Edit

Libraries: Add/Edit

Description: Add/Edit

Using computer vision to detect lane lines (Udacity Self Driving Car Nanodegree P4)

0