@article {london:jmlr16, title = {Stability and Generalization in Structured Prediction}, journal = {Journal of Machine Learning Research}, volume = {17}, year = {2016}, note = {to appear}, chapter = {1--52}, abstract = {

Structured prediction models have been found to learn effectively from a few large examples\ {\textemdash} sometimes even just one. Despite empirical evidence, canonical learning theory cannot guarantee generalization in this setting because the error bounds decrease as a function of the number of examples. We therefore propose new PAC-Bayesian generalization bounds for structured prediction that decrease as a function of both the number of examples and the size of each example. Our analysis hinges on the stability of joint inference and the smoothness of the data distribution. We apply our bounds to several common learning scenarios, including max-margin and soft-max training of Markov random fields. Under certain conditions, the resulting error bounds can be far more optimistic than previous results and can even guarantee generalization from a single large example.

}, keywords = {PAC-Bayes, generalization bounds, learning theory, structured prediction}, author = {Ben London and Bert Huang and Lise Getoor} }