Concentration and Confidence for Discrete Bayesian Sequence Predictors
Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only limited results on the distribution of this error. We prove tight high-probability bounds on the cumulative error, which is measured in terms of the Kullback-Leibler (KL) divergence. We also consider the problem of constructing upper confidence bounds on the KL and Hellinger errors similar to those constructed from Hoeffding-like bounds in the i.i.d. case. The new results are applied to show that Bayesian sequence prediction can be used in the Knows What It Knows (KWIK) framework with bounds that match the state-of-the-art.
KeywordsBayesian sequence prediction concentration of measure information theory KWIK learning
Unable to display preview. Download preview PDF.
- [DLL09]Diuk, C., Li, L., Leffler, B.: The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning. In: Danyluk, A.P., Bottou, L., Littman, M.L. (eds.) Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 249–256. ACM (2009)Google Scholar
- [Hut05]Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2005)Google Scholar
- [LHS13]Lattimore, T., Hutter, M., Sunehag, P.: Concentration and confidence for discrete Bayesian predictors. Technical report (2013), http://arxiv.org/abs/1307.0127
- [Vil39]Ville, J.: Etude critique de la notion de collectif. Gauthier-Villars, Paris (1939)Google Scholar