Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes

Details Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes

2009-09-10

arxiv.org/abs/0909.1933v2

Computer Science

Learning

Long version of the AISTATS 09 paper: http://jmlr.csail.mit.edu/proceedings/papers/v5/ralaivola09a/ralaivola09a.pdf

Scientific paper

Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for margin classifiers: there have been recent contributions showing how practical these bounds can be either to perform model selection (Ambroladze et al., 2007) or even to directly guide the learning of linear classifiers (Germain et al., 2009). However, there are many practical situations where the training data show some dependencies and where the traditional IID assumption does not hold. Stating generalization bounds for such frameworks is therefore of the utmost interest, both from theoretical and practical standpoints. In this work, we propose the first - to the best of our knowledge - Pac-Bayes generalization bounds for classifiers trained on data exhibiting interdependencies. The approach undertaken to establish our results is based on the decomposition of a so-called dependency graph that encodes the dependencies within the data, in sets of independent data, thanks to graph fractional covers. Our bounds are very general, since being able to find an upper bound on the fractional chromatic number of the dependency graph is sufficient to get new Pac-Bayes bounds for specific settings. We show how our results can be used to derive bounds for ranking statistics (such as Auc) and classifiers trained on data distributed according to a stationary {\ss}-mixing process. In the way, we show how our approach seemlessly allows us to deal with U-processes. As a side note, we also provide a Pac-Bayes generalization bound for classifiers learned on data from stationary $\varphi$-mixing distributions.

Affiliated with

Also associated with

No associations

Rating

Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes 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 Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Chromatic PAC-Bayes Bounds for Non-IID Data: Applications to Ranking and Stationary $β$-Mixing Processes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-131627