Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?

We could not so far claim that deep networks trained with stochastic gradient descent are Bayesian. And it may be because SGD biases learning towards flat minima, rather than sharp minima. It turns out, (Hochreiter and Schmidhuber, 1997) motivated their work on seeking flat minima from a Bayesian, minimum description length perspective. Seeking flat minima makes sense from a minimum description length perspective.