Search Results for author: Michael Brand

Found 4 papers, 0 papers with code

The IMP game: Learnability, approximability and adversarial learning beyond $Σ^0_1$

no code implementations7 Feb 2016 Michael Brand, David L. Dowe

We introduce a problem set-up we call the Iterated Matching Pennies (IMP) game and show that it is a powerful framework for the study of three problems: adversarial learnability, conventional (i. e., non-adversarial) learnability and approximability.

MML is not consistent for Neyman-Scott

no code implementations14 Oct 2016 Michael Brand

Strict Minimum Message Length (SMML) is an information-theoretic statistical inference method widely cited (but only with informal arguments) as providing estimations that are consistent for general estimation problems.

RKL: a general, invariant Bayes solution for Neyman-Scott

no code implementations20 Jul 2017 Michael Brand

Neyman-Scott is a classic example of an estimation problem with a partially-consistent posterior, for which standard estimation methods tend to produce inconsistent results.

Risk-averse estimation, an axiomatic approach to inference, and Wallace-Freeman without MML

no code implementations28 Jun 2018 Michael Brand

We define a new class of Bayesian point estimators, which we refer to as risk averse.

Cannot find the paper you are looking for? You can Submit a new open access paper.