30 citations · 125 across the 26 of their papers we have counts for
24 papers · 1 filter
On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm
Julien Bastian, Benjamin Leblanc, Pascal Germain +4
Weighted majority votes are central to many successful ensemble methods. PAC-Bayesian theory provides tight generalization guarantees for such models by analyzing the expected risk…
PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifiers
Julien Bastian, Benjamin Leblanc, Pascal Germain +5
Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing…
PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
Hind Atbir, Farah Cherfaoui, Guillaume Metzler +2
PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this li…
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
Paul Viallard, Rémi Emonet, Amaury Habrard +2
In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds,…
Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
Paul Viallard, Pascal Germain, Amaury Habrard +1
In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of i…
A General Framework for the Practical Disintegration of PAC-Bayesian Bounds
Paul Viallard, Pascal Germain, Amaury Habrard +1
PAC-Bayesian bounds are known to be tight and informative when studying the generalization ability of randomized classifiers. However, they require a loose and costly derandomizati…
Metric Learning from Imbalanced Data
Léo Gautheron, Emilie Morvant, Amaury Habrard +1
A key element of any machine learning algorithm is the use of a function that measures the dis/similarity between data points. Given a task, such a function can be optimized with a…
Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting
Léo Gautheron, Pascal Germain, Amaury Habrard +3
We propose a Gradient Boosting algorithm for learning an ensemble of kernel functions adapted to the task at hand. Unlike state-of-the-art Multiple Kernel Learning techniques that…
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…
Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters
Anil Goyal, Emilie Morvant, Pascal Germain +1
In this paper we propose a boosting based multiview learning algorithm, referred to as PB-MVBoost, which iteratively learns i) weights over view-specific voters capturing view-spec…
Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization
Anil Goyal, Emilie Morvant, Massih-Reza Amini
We tackle the issue of classifier combinations when observations have multiple views. Our method jointly learns view-specific weighted majority vote classifiers (i.e. for each view…
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…
PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach
Anil Goyal, Emilie Morvant, Pascal Germain +1
We study a two-level multiview learning with more than two views under the PAC-Bayesian framework. This approach, sometimes referred as late fusion, consists in learning sequential…
A New PAC-Bayesian Perspective on Domain Adaptation
Pascal Germain, Amaury Habrard, François Laviolette +1
We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a…
PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
Pascal Germain, Amaury Habrard, François Laviolette +1
In this paper, 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 majorit…
An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context
Pascal Germain, Amaury Habrard, Francois Laviolette +1
This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germ…
On Generalizing the C-Bound to the Multiclass and Multi-label Settings
Francois Laviolette, Emilie Morvant, Liva Ralaivola +1
The C-bound, introduced in Lacasse et al., gives a tight upper bound on the risk of a binary majority vote classifier. In this work, we present a first step towards extending this…
Domain adaptation of weighted majority votes via perturbed variation-based self-labeling
Emilie Morvant
In machine learning, the domain adaptation problem arrives when the test (target) and the train (source) data are generated from different distributions. A key applied issue is thu…
On the Generalization of the C-Bound to Structured Output Ensemble Methods
François Laviolette, Emilie Morvant, Liva Ralaivola +1
This paper generalizes an important result from the PAC-Bayesian literature for binary classification to the case of ensemble methods for structured outputs. We prove a generic ver…
Majority Vote of Diverse Classifiers for Late Fusion
Emilie Morvant, Amaury Habrard, Stéphane Ayache
In the past few years, a lot of attention has been devoted to multimedia indexing by fusing multimodal informations. Two kinds of fusion schemes are generally considered: The early…
Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer
Emilie Morvant
We tackle the PAC-Bayesian Domain Adaptation (DA) problem. This arrives when one desires to learn, from a source distribution, a good weighted majority vote (over a set of classifi…
PAC-Bayesian Learning and Domain Adaptation
Pascal Germain, Amaury Habrard, François Laviolette +1
In machine learning, Domain Adaptation (DA) arises when the distribution gen- erating the test (target) data differs from the one generating the learning (source) data. It is well…
PAC-Bayesian Majority Vote for Late Classifier Fusion
Emilie Morvant, Amaury Habrard, Stéphane Ayache
A lot of attention has been devoted to multimedia indexing over the past few years. In the literature, we often consider two kinds of fusion schemes: The early fusion and the late…
PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification
Emilie Morvant, Sokol Koço, Liva Ralaivola
In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical…