Benjamin Guedj

research

∙ 09/08/2023

Generalization Bounds: Perspectives from Information Theory and PAC-Bayes

A fundamental question in theoretical machine learning is generalization...

0 Fredrik Hellström, et al. ∙

research

∙ 06/07/2023

Learning via Wasserstein-Based High Probability Generalisation Bounds

Minimising upper bounds on the population risk or the generalisation gap...

16 Paul Viallard, et al. ∙

research

∙ 04/14/2023

Wasserstein PAC-Bayes Learning: A Bridge Between Generalisation and Optimisation

PAC-Bayes learning is an established framework to assess the generalisat...

1 Maxime Haddouche, et al. ∙

research

∙ 01/18/2023

Optimistic Dynamic Regret Bounds

Online Learning (OL) algorithms have originally been developed to guaran...

20 Maxime Haddouche, et al. ∙

research

∙ 10/20/2022

Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty

We introduce a modified version of the excess risk, which can be used to...

16 Felix Biggs, et al. ∙

research

∙ 10/03/2022

PAC-Bayes with Unbounded Losses through Supermartingales

While PAC-Bayes is now an established learning framework for bounded los...

24 Maxime Haddouche, et al. ∙

research

∙ 09/06/2022

A PAC-Bayes bound for deterministic classifiers

We establish a disintegrated PAC-Bayesian bound, for classifiers that ar...

19 Eugenio Clerico, et al. ∙

research

∙ 06/18/2022

Efficient Aggregated Kernel Tests using Incomplete U-statistics

We propose a series of computationally efficient, nonparametric tests fo...

8 Antonin Schrab, et al. ∙

research

∙ 06/09/2022

On Margins and Generalisation for Voting Classifiers

We study the generalisation properties of majority voting on finite ense...

25 Felix Biggs, et al. ∙

research

∙ 05/31/2022

Online PAC-Bayes Learning

Most PAC-Bayesian bounds hold in the batch learning setting where data i...

59 Maxime Haddouche, et al. ∙

research

∙ 04/26/2022

Reprint: a randomized extrapolation based on principal components for data augmentation

Data scarcity and data imbalance have attracted a lot of attention in ma...

30 Jiale Wei, et al. ∙

research

∙ 02/23/2022

On PAC-Bayesian reconstruction guarantees for VAEs

Despite its wide use and empirical successes, the theoretical understand...

55 Badr-Eddine Chérief-Abdellatif, et al. ∙

research

∙ 02/11/2022

Measuring dissimilarity with diffeomorphism invariance

Measures of similarity (or dissimilarity) are a key ingredient to many m...

37 Théophile Cantelobre, et al. ∙

research

∙ 02/11/2022

On change of measure inequalities for f-divergences

We propose new change of measure inequalities based on f-divergences (of...

30 Antoine Picard-Weibel, et al. ∙

research

∙ 02/11/2022

Controlling Confusion via Generalisation Bounds

We establish new generalisation bounds for multiclass classification by ...

10 Reuben Adams, et al. ∙

research

∙ 02/03/2022

Non-Vacuous Generalisation Bounds for Shallow Neural Networks

We focus on a specific class of shallow neural networks with a single hi...

3 Felix Biggs, et al. ∙

research

∙ 02/02/2022

KSD Aggregated Goodness-of-fit Test

We investigate properties of goodness-of-fit tests based on the Kernel S...

9 Antonin Schrab, et al. ∙

research

∙ 11/15/2021

Progress in Self-Certified Neural Networks

A learning method is self-certified if it uses all available data to sim...

23 Maria Perez-Ortiz, et al. ∙

research

∙ 10/28/2021

MMD Aggregated Two-Sample Test

We propose a novel nonparametric two-sample test based on the Maximum Me...

3 Antonin Schrab, et al. ∙

research

∙ 09/21/2021

Learning PAC-Bayes Priors for Probabilistic Neural Networks

Recent works have investigated deep learning models trained by optimisin...

18 Maria Perez-Ortiz, et al. ∙

research

∙ 07/08/2021

On Margins and Derandomisation in PAC-Bayes

We develop a framework for derandomising PAC-Bayesian generalisation bou...

17 Felix Biggs, et al. ∙

research

∙ 06/23/2021

Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound

We investigate a stochastic counterpart of majority votes over finite en...

9 Valentina Zantedeschi, et al. ∙

research

∙ 12/18/2020

Upper and Lower Bounds on the Performance of Kernel PCA

Principal Component Analysis (PCA) is a popular method for dimension red...

12 Maxime Haddouche, et al. ∙

research

∙ 12/07/2020

A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings

Many practical machine learning tasks can be framed as Structured predic...

9 Théophile Cantelobre, et al. ∙

research

∙ 11/24/2020

An end-to-end data-driven optimisation framework for constrained trajectories

Many real-world problems require to optimise trajectories under constrai...

9 Florent Dewez, et al. ∙

research

∙ 11/16/2020

Cluster-Specific Predictions with Multi-Task Gaussian Processes

A model involving Gaussian processes (GPs) is introduced to simultaneous...

6 Arthur Leroy, et al. ∙

research

∙ 09/22/2020

Forecasting elections results via the voter model with stubborn nodes

In this paper we propose a novel method to forecast the result of electi...

0 Antoine Vendeville, et al. ∙

research

∙ 07/21/2020

MAGMA: Inference and Prediction with Multi-Task Gaussian Processes

We investigate the problem of multiple time series forecasting, with the...

15 Arthur Leroy, et al. ∙

research

∙ 06/26/2020

PAC-Bayesian Bound for the Conditional Value at Risk

Conditional Value at Risk (CVaR) is a family of "coherent risk measures"...

3 Zakaria Mhammedi, et al. ∙

research

∙ 06/22/2020

Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks

We make three related contributions motivated by the challenge of traini...

11 Felix Biggs, et al. ∙

research

∙ 06/12/2020

PAC-Bayes unleashed: generalisation bounds with unbounded losses

We present new PAC-Bayesian generalisation bounds for learning problems ...

7 Maxime Haddouche, et al. ∙

research

∙ 06/12/2020

How opinions crystallise: an analysis of polarisation in the voter model

We address the phenomenon of sedimentation of opinions in networks. We i...

0 Antoine Vendeville, et al. ∙

research

∙ 05/11/2020

From industry-wide parameters to aircraft-centric on-flight inference: improving aeronautics performance prediction with machine learning

Aircraft performance models play a key role in airline operations, espec...

39 Florent Dewez, et al. ∙

research

∙ 12/17/2019

Kernel-Based Ensemble Learning in Python

We propose a new supervised learning algorithm, for classification and r...

35 Benjamin Guedj, et al. ∙

research

∙ 10/10/2019

PAC-Bayesian Contrastive Unsupervised Representation Learning

Contrastive unsupervised representation learning (CURL) is the state-of-...

15 Kento Nozawa, et al. ∙

research

∙ 10/10/2019

Still no free lunches: the price to pay for tighter PAC-Bayes bounds

"No free lunch" results state the impossibility of obtaining meaningful ...

20 Benjamin Guedj, et al. ∙

research

∙ 09/15/2019

Online k-means Clustering

We study the problem of online clustering where a clustering algorithm h...

6 Vincent Cohen-Addad, et al. ∙

research

∙ 05/31/2019

PAC-Bayes Un-Expected Bernstein Inequality

We present a new PAC-Bayesian generalization bound. Standard bounds cont...

0 Zakaria Mhammedi, et al. ∙

research

∙ 05/27/2019

Attributing and Referencing (Research) Software: Best Practices and Outlook from Inria

Software is a fundamental pillar of modern scientiic research, not only ...

0 Pierre Alliez, et al. ∙

research

∙ 05/24/2019

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks

We present a comprehensive study of multilayer neural networks with bina...

2 Gaël Letarte, et al. ∙

research

∙ 05/24/2019

Perturbed Model Validation: A New Framework to Validate Model Relevance

This paper introduces PMV (Perturbed Model Validation), a new technique ...

3 Jie M. Zhang, et al. ∙

research

∙ 04/01/2019

Non-linear aggregation of filters to improve image denoising

We introduce a novel aggregation method to efficiently perform image den...

0 Benjamin Guedj, et al. ∙

research

∙ 03/11/2019

Revisiting clustering as matrix factorisation on the Stiefel manifold

This paper studies clustering for possibly high dimensional data (e.g. i...

0 Stéphane Chrétien, et al. ∙

research

∙ 01/16/2019

A Primer on PAC-Bayesian Learning

Generalized Bayesian learning algorithms are increasingly popular in mac...

0 Benjamin Guedj, et al. ∙

research

∙ 05/18/2018

Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly

When confronted with massive data streams, summarizing data with dimensi...

0 Benjamin Guedj, et al. ∙

research

∙ 04/26/2018

Decentralized learning with budgeted network load using Gaussian copulas and classifier ensembles

We examine a network of learners which address the same classification t...

0 John Klein, et al. ∙

research

∙ 04/25/2017

Pycobra: A Python Toolbox for Ensemble Learning and Visualisation

We introduce pycobra, a Python library devoted to ensemble learning (reg...

0 Benjamin Guedj, et al. ∙

research

∙ 10/23/2016

Simpler PAC-Bayesian Bounds for Hostile Data

PAC-Bayesian learning bounds are of the utmost interest to the learning ...

0 Pierre Alquier, et al. ∙

research

∙ 08/23/2016

Stability revisited: new generalisation bounds for the Leave-one-Out

The present paper provides a new generic strategy leading to non-asympto...

0 Alain Celisse, et al. ∙

research

∙ 02/01/2016

A Quasi-Bayesian Perspective to Online Clustering

When faced with high frequency streams of data, clustering raises theore...

0 Le Li, et al. ∙

Benjamin Guedj

Featured Co-authors