PAC-Bayesian Contrastive Unsupervised Representation Learning
Kento Nozawa, Pascal Germain, Benjamin Guedj
Abstract
Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data. While CURL has collected several empirical successes recently, theoretical understanding of its performance was still missing. In a recent work, Arora et al. (2019) provide the first generalisation bounds for CURL, relying on a Rademacher complexity. We extend their framework to the flexible PAC-Bayes setting, allowing to deal with the non-iid setting. We present PAC-Bayesian generalisation bounds for CURL, which are then used to derive a new representation learning algorithm. Numerical experiments on real-life datasets illustrate that our algorithm achieves competitive accuracy, and yields non-vacuous generalisation bounds.
BibTeX
@InProceedings{pmlr-v124-nozawa20a,
title = {PAC-Bayesian Contrastive Unsupervised Representation Learning},
author = {Nozawa, Kento and Germain, Pascal and Guedj, Benjamin},
booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)},
pages = {21--30},
year = {2020},
editor = {Peters, Jonas and Sontag, David},
volume = {124},
series = {Proceedings of Machine Learning Research},
month = {03--06 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v124/nozawa20a/nozawa20a.pdf},
url = {https://proceedings.mlr.press/v124/nozawa20a.html},
abstract = {Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data. While CURL has collected several empirical successes recently, theoretical understanding of its performance was still missing. In a recent work, Arora et al. (2019) provide the first generalisation bounds for CURL, relying on a Rademacher complexity. We extend their framework to the flexible PAC-Bayes setting, allowing to deal with the non-iid setting. We present PAC-Bayesian generalisation bounds for CURL, which are then used to derive a new representation learning algorithm. Numerical experiments on real-life datasets illustrate that our algorithm achieves competitive accuracy, and yields non-vacuous generalisation bounds.}
}