In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
The majority of theoretical work in machine learning is done under the assumption of exchangeability: essentially, it is assumed that the examples are generated from the same prob...
Vladimir Vovk, Ilia Nouretdinov, Alexander Gammerm...
We consider on-line density estimation with the multivariate Gaussian distribution. In each of a sequence of trials, the learner must posit a mean µ and covariance Σ; the learner...
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...