Perez-Ortiz, M;
Rivasplata, O;
Parrado-Hernandez, E;
Guedj, B;
Shawe-Taylor, J;
(2021)
Progress in Self-Certified Neural Networks.
In:
Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021).
NeurIPS
Preview |
Text
2111.07737v1.pdf - Accepted Version Download (599kB) | Preview |
Abstract
A learning method is self-certified if it uses all available data to simultaneously learn a predictor and certify its quality with a tight statistical certificate that is valid on unseen data. Recent work has shown that neural network models trained by optimising PAC-Bayes bounds lead not only to accurate predictors, but also to tight risk certificates, bearing promise towards achieving self-certified learning. In this context, learning and certification strategies based on PAC-Bayes bounds are especially attractive due to their ability to leverage all data to learn a posterior and simultaneously certify its risk with a tight numerical certificate. In this paper, we assess the progress towards self-certification in probabilistic neural networks learnt by PAC-Bayes inspired objectives. We empirically compare (on 4 classification datasets) classical test set bounds for deterministic predictors and a PAC-Bayes bound for randomised self-certified predictors. We first show that both of these generalisation bounds are not too far from out-of-sample test set errors. We then show that in data starvation regimes, holding out data for the test set bounds adversely affects generalisation performance, while self-certified strategies based on PAC-Bayes bounds do not suffer from this drawback, proving that they might be a suitable choice for the small data regime. We also find that probabilistic neural networks learnt by PAC-Bayes inspired objectives lead to certificates that can be surprisingly competitive with commonly used test set bounds.
Type: | Proceedings paper |
---|---|
Title: | Progress in Self-Certified Neural Networks |
Event: | NeurIPS 2021 workshop: Bayesian Deep Learning |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://papers.nips.cc/paper/2021 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics |
URI: | https://discovery.ucl.ac.uk/id/eprint/10138739 |
Archive Staff Only
![]() |
View Item |