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

7 Feb 2016Michael BrandDavid 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. Using it, we are able to derive the following theorems... (read more)

PDF Abstract