On Margins and Derandomisation in PAC-Bayes

07/08/2021
by   Felix Biggs, et al.
17

We develop a framework for derandomising PAC-Bayesian generalisation bounds achieving a margin on training data, relating this process to the concentration-of-measure phenomenon. We apply these tools to linear prediction, single-hidden-layer neural networks with an unusual erf activation function, and deep ReLU networks, obtaining new bounds. The approach is also extended to the idea of "partial-derandomisation" where only some layers are derandomised and the others are stochastic. This allows empirical evaluation of single-hidden-layer networks on more complex datasets, and helps bridge the gap between generalisation bounds for non-stochastic deep networks and those for randomised deep networks as generally examined in PAC-Bayes.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset