164 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University College LondonGB15 papers
- Institut national de recherche en sciences et technologies du numériqueFR13 papers
- Modélisation aléatoire de Paris NanterreFR13 papers
- University of LondonGB8 papers
- Centre Inria de l'Université de LilleFR7 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- Laboratoire de Probabilités et Modèles AléatoiresFR5 papers
- Université Paris NanterreFR5 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR3 papers
- Institut de Mathématiques de MarseilleFR3 papers
- Université de LilleFR3 papers
- University of OxfordGB3 papers
6 papers · 1 filter
PAC-Bayesian Contrastive Unsupervised Representation Learning
Kento Nozawa, Pascal Germain, Benjamin Guedj
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 colle…
Online k-means Clustering
Vincent Cohen-Addad, Benjamin Guedj, Varun Kanade +1
We study the problem of online clustering where a clustering algorithm has to assign a new point that arrives to one of clusters. The specific formulation we use is the -mea…
Ranking and synchronization from pairwise measurements via SVD
Alexandre d'Aspremont, Mihai Cucuringu, Hemant Tyagi
Given a measurement graph and an unknown signal , we investigate algorithms for recovering from pairwise measurements of the form ; $\…
PAC-Bayes Un-Expected Bernstein Inequality
Zakaria Mhammedi, Peter D. Grunwald, Benjamin Guedj
We present a new PAC-Bayesian generalization bound. Standard bounds contain a $\sqrt{L_n \cdot \KL/n}$ complexity term which dominates unless , the empirical error of the lear…
Non-linear aggregation of filters to improve image denoising
Benjamin Guedj, Juliette Rengot
We introduce a novel aggregation method to efficiently perform image denoising. Preliminary filters are aggregated in a non-linear fashion, using a new metric of pixel proximity ba…
A Primer on PAC-Bayesian Learning
Benjamin Guedj
Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalisation properties and flexibility. The present paper aims at providi…