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
40 papers
Seeded graph matching for the correlated Gaussian Wigner model via the projected power method
Ernesto Araya, Guillaume Braun, Hemant Tyagi
In the \emph{graph matching} problem we observe two graphs and the goal is to find an assignment (or matching) between their vertices such that some measure of edge agreement…
Model-based Clustering with Missing Not At Random Data
Aude Sportisse, Matthieu Marbac, Fabien Laporte +4
Model-based unsupervised learning, as any learning task, stalls as soon as missing data occurs. This is even more true when the missing data are informative, or said missing not at…
Upper and Lower Bounds on the Performance of Kernel PCA
Maxime Haddouche, Benjamin Guedj, John Shawe-Taylor
Principal Component Analysis (PCA) is a popular method for dimension reduction and has attracted an unfailing interest for decades. More recently, kernel PCA (KPCA) has emerged as…
Learning Binary Decision Trees by Argmin Differentiation
Valentina Zantedeschi, Matt J. Kusner, Vlad Niculae
We address the problem of learning binary decision trees that partition data for some downstream task. We propose to learn discrete parameters (i.e., for tree traversals and node p…
MAGMA: Inference and Prediction with Multi-Task Gaussian Processes
Arthur Leroy, Pierre Latouche, Benjamin Guedj +1
A novel multi-task Gaussian process (GP) framework is proposed, by using a common mean process for sharing information across tasks. In particular, we investigate the problem of ti…
PAC-Bayesian Bound for the Conditional Value at Risk
Zakaria Mhammedi, Benjamin Guedj, Robert C. Williamson
Conditional Value at Risk (CVaR) is a family of "coherent risk measures" which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garne…
Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks
Felix Biggs, Benjamin Guedj
We make three related contributions motivated by the challenge of training stochastic neural networks, particularly in a PAC-Bayesian setting: (1) we show how averaging over an ens…
From industry-wide parameters to aircraft-centric on-flight inference: improving aeronautics performance prediction with machine learning
Florent Dewez, Benjamin Guedj, Vincent Vandewalle
Aircraft performance models play a key role in airline operations, especially in planning a fuel-efficient flight. In practice, manufacturers provide guidelines which are slightly…
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…
Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior
Gaël Letarte, Emilie Morvant, Pascal Germain
We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory. While the primary goal of RFF is to approximate a kern…
Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly
Benjamin Guedj, Le Li
When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. Principal curves act as a nonl…
Decentralized learning with budgeted network load using Gaussian copulas and classifier ensembles
John Klein, Mahmoud Albardan, Benjamin Guedj +1
We examine a network of learners which address the same classification task but must learn from different data sets. The learners cannot share data but instead share their models.…
Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping
Mihai Cucuringu, Hemant Tyagi
Consider an unknown smooth function , and say we are given noisy mod 1 samples of , i.e., , for $x_i \in [0,1]…
PAC-Bayes and Domain Adaptation
Pascal Germain, Amaury Habrard, François Laviolette +1
We provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a dif…
Pycobra: A Python Toolbox for Ensemble Learning and Visualisation
Benjamin Guedj, Bhargav Srinivasa Desikan
We introduce \texttt{pycobra}, a Python library devoted to ensemble learning (regression and classification) and visualisation. Its main assets are the implementation of several en…
Simpler PAC-Bayesian Bounds for Hostile Data
Pierre Alquier, Benjamin Guedj
PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution to its emp…
Convex lattice polygonal lines with a constrained number of vertices
Julien Bureaux, Nathanaël Enriquez
A detailed combinatorial analysis of planar convex lattice polygonal lines is presented. This makes it possible to answer an open question of Vershik regarding the existence of a l…
The discriminative functional mixture model for a comparative analysis of bike sharing systems
Charles Bouveyron, Etienne Côme, Julien Jacques
Bike sharing systems (BSSs) have become a means of sustainable intermodal transport and are now proposed in many cities worldwide. Most BSSs also provide open access to their data,…
PAC-Bayesian High Dimensional Bipartite Ranking
Benjamin Guedj, Sylvain Robbiano
This paper is devoted to the bipartite ranking problem, a classical statistical learning task, in a high dimensional setting. We propose a scoring and ranking strategy based on the…