Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families

no code implementations • 19 May 2013 • Peter Bartlett, Peter Grunwald, Peter Harremoes, Fares Hedayati, Wojciech Kotlowski

Keywords: SNML Exchangeability, Exponential Family, Online Learning, Logarithmic Loss, Bayesian Strategy, Jeffreys Prior, Fisher Information1

Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (2010)

no code implementations • 11 May 2012 • Peter Grunwald, Peter Spirtes

This is the Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence, which was held on Catalina Island, CA, July 8 - 11 2010.

Shannon Information and Kolmogorov Complexity

no code implementations • 1 Oct 2004 • Peter Grunwald, Paul Vitanyi

We compare the elementary theories of Shannon information and Kolmogorov complexity, the extent to which they have a common purpose, and where they are fundamentally different.

Information Theory Information Theory E.4, H.1.1

A tutorial introduction to the minimum description length principle

1 code implementation • 4 Jun 2004 • Peter Grunwald

This tutorial provides an overview of and introduction to Rissanen's Minimum Description Length (MDL) Principle.