Rivasplata, O;
Parrado-Hernández, E;
Shawe-Taylor, J;
Sun, S;
Szepesvári, C;
(2018)
PAC-Bayes bounds for stable algorithms with instance-dependent priors.
In: Bengio, S and Wallach, HM and Larochelle, H and Grauman, K and Cesa-Bianchi, N, (eds.)
Proceedings of the 32nd International Conference on Neural Information Processing Systems - NIPS'18.
(pp. pp. 9234-9244).
Association for Computing Machinery (ACM): Montréal, Canada.
Preview |
Text
paper_plussupp.pdf - Accepted Version Download (509kB) | Preview |
Abstract
PAC-Bayes bounds have been proposed to get risk estimates based on a training sample. In this paper the PAC-Bayes approach is combined with stability of the hypothesis learned by a Hilbert space valued algorithm. The PAC-Bayes setting is used with a Gaussian prior centered at the expected output. Thus a novelty of our paper is using priors defined in terms of the data-generating distribution. Our main result estimates the risk of the randomized algorithm in terms of the hypothesis stability coefficients. We also provide a new bound for the SVM classifier, which is compared to other known bounds experimentally. Ours appears to be the first uniform hypothesis stability-based bound that evaluates to non-trivial values.
| Type: | Proceedings paper |
|---|---|
| Title: | PAC-Bayes bounds for stable algorithms with instance-dependent priors |
| Event: | 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), 2 - 8 December 2018, Montreal, Canada. |
| Location: | Montreal, Canada |
| Dates: | 02 December 2018 - 08 December 2018 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.5555/3327546.3327595 |
| Publisher version: | https://doi.org/10.5555/3327546.3327595 |
| 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/10067406 |
Archive Staff Only
 |
View Item |
