Adversarial networks can be viewed as different agents competing against each other. But beyond that, I don't see how game theory is relevant or what insights it provides. This article is super vague and confusing to me.
>Where do these regularizations come from and how can we select a good regularization? How do we handle impartial information? This is where a game theoretic viewpoint becomes important. Generalization is sometimes referred to as ‘structural risk minimization’.
Ok... and what useful insight do the game theorists have here? He doesn't elaborate at all. Regularization is a very well studied concept already. I don't see how this is connected to game theory at all. Regularization is all about priors and Occam's razor.
>Where do these regularizations come from and how can we select a good regularization? How do we handle impartial information? This is where a game theoretic viewpoint becomes important. Generalization is sometimes referred to as ‘structural risk minimization’.
Ok... and what useful insight do the game theorists have here? He doesn't elaborate at all. Regularization is a very well studied concept already. I don't see how this is connected to game theory at all. Regularization is all about priors and Occam's razor.