A Generalisation Signal Need Not Be a Model-Selection Signal
Model selection in computational biology often relies on validation data drawn from the training regime, even when deployment lies outside it. When validation no longer preserves which model is best, a natural alternative is to rank candidates using properties of the trained network itself. We test this idea using a novel, forward-only proxy motivated by the norm of the Hessian, alongside common…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
