Work

Conditional Gaussian PAC-Bayes.

Year: 2021
Type: preprint
Abstract: Recent studies have empirically investigated different methods to train a stochastic classifier by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures need to replace the misclassification error with a surrogate loss, leading to a mismatch between the optimisation objective and the actual generalisation bound. The present paper proposes a novel training algorithm that optimises the PAC-Bayesian bound, without relying on any surrogate loss. Empirical results show that the bounds obtained with this approach are tighter than those found in the literature.
Language: English
Open Access status: green
OpenAlex ID: W3210935491
Cites: 30
Cited by:
Related to: 10