HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

PAC-Bayesian Contrastive Unsupervised Representation Learning

Kento Nozawa 1, 2 Pascal Germain 3 Benjamin Guedj 4, 5, 6, 3, 7
3 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies
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 generalisation bounds with non-vacuous values.
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download

Contributor : Benjamin Guedj Connect in order to contact the contributor
Submitted on : Monday, December 9, 2019 - 9:11:54 PM
Last modification on : Wednesday, March 23, 2022 - 3:51:07 PM
Long-term archiving on: : Tuesday, March 10, 2020 - 10:17:49 PM


Files produced by the author(s)


  • HAL Id : hal-02401282, version 1
  • ARXIV : 1910.04464


Kento Nozawa, Pascal Germain, Benjamin Guedj. PAC-Bayesian Contrastive Unsupervised Representation Learning. UAI 2020 - Conference on Uncertainty in Artificial Intelligence, Aug 2020, Toronto, Canada. ⟨hal-02401282⟩



Record views


Files downloads