Research Project: Generalised Maximum Entropy Classification
The emergence of new challenging real-world applications has exposed serious issues with current approaches to model adaptation in machine learning. Existing theory and algorithms focus on fitting the available training data, but cannot provide worst-case guarantees in mission-critical applications. Vapnik's statistical learning theory is useless for model selection, as the bounds on generalisation errors it predicts are too wide to be useful, and rely on the assumption that training and testing data come from the same (unknown) distribution. The crucial question is: what exactly can one infer from a training set?

Max entropy classifiers provide a signficant example, due to their simplicity and widespread application. There, the entropy of the sought joint (or conditional) probability distribution of data and class is maximised, following the maximum entropy principle that the least informative distribution which matches the available evidence should be chosen. Having picked a set of feature functions, selected to efficiently encode the training information, the joint distribution is subject to the constraint that their empirical expectation equals that associated with the max entropy distribution. The assumptions that (i) training and test data come from the same probability distribution, and that (ii) the empirical expectation of the training data is correct, and the model expectation should match it, are rather strong, and work against generalisation power.

A way around this issue is to adopt as models convex sets of probability distributions, rather than standard probability measures.
Relevant papers:
  •   Fabio Cuzzolin
    The geometry of uncertainty - The geometry of imprecise probabilities
    Artificial Intelligence: Foundations, Theory, and Algorithms (, Springer-Verlag, 2018 (in press)
    The geometry of uncertainty
  • Fabio Cuzzolin
    Generalised max entropy classifiers
    Proceedings of the Fifth International Conference on the Theory of Belief Functions (BELIEF 2018)
    Compiegne, France, September 2018