Concentration and confidence for discrete Bayesian sequence predictors

DOI10.1007/978-3-642-40935-6_23MaRDI QIDQ2859227zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Tor Lattimore, Marcus Hutter, Peter Sunehag

Publication date 6 November 2013

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1307.0127

zbMATH Keywords

Bayesian sequence predictionconcentration of measureinformation theoryKWIK learning

Mathematics Subject Classification ID

Bayesian inference (62F15) Inference from stochastic processes and prediction (62M20) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: 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.

Recommendations

• Convergence and loss bounds for bayesian sequence prediction
• 10.1162/1532443041827952
• Consistency of discrete Bayesian learning
• On universal prediction and Bayesian confirmation
• On the Consistency of Discrete Bayesian Learning

Cited in

(3)

• Convergence and loss bounds for bayesian sequence prediction
• Learning Theory
• Learning Theory

This page was built for publication: Concentration and confidence for discrete Bayesian sequence predictors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2859227)