1 code implementation • 19 Feb 2024 • Paul Viallard, Rémi Emonet, Amaury Habrard, Emilie Morvant, Valentina Zantedeschi
In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework.
1 code implementation • 30 Oct 2023 • Quentin Bouniot, Angélique Loesch, Romaric Audigier, Amaury Habrard
For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives.
no code implementations • 25 Oct 2023 • Quentin Bouniot, Romaric Audigier, Angélique Loesch, Amaury Habrard
However, for unsupervised pretraining, the popular contrastive learning requires a large batch size and, therefore, a lot of resources.
no code implementations • 26 Sep 2022 • Yacouba Kaloga, Pierre Borgnat, Amaury Habrard
Therefore, many metric learning algorithms have been developed in recent years, mainly for Euclidean data in order to improve performance of classification or clustering methods.
1 code implementation • NeurIPS 2021 • Valentina Zantedeschi, Paul Viallard, Emilie Morvant, Rémi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj
We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties.
1 code implementation • 28 Apr 2021 • Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
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 its margin (i. e., the expected margin and the voters' diversity).
1 code implementation • NeurIPS 2021 • Paul Viallard, Guillaume Vidot, Amaury Habrard, Emilie Morvant
We propose the first general PAC-Bayesian generalization bounds for adversarial robustness, that estimate, at test time, how much a model will be invariant to imperceptible perturbations in the input.
1 code implementation • 17 Feb 2021 • Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant
PAC-Bayesian bounds are known to be tight and informative when studying the generalization ability of randomized classifiers.
no code implementations • 30 Oct 2020 • Yacouba Kaloga, Pierre Borgnat, Sundeep Prabhakar Chepuri, Patrice Abry, Amaury Habrard
We present a novel multiview canonical correlation analysis model based on a variational approach.
1 code implementation • 5 Oct 2020 • Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task.
no code implementations • 28 Sep 2020 • Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard
To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of meta-learning theory into practice for the popular task of few-shot classification.
1 code implementation • 7 Jul 2020 • Louis Béthune, Yacouba Kaloga, Pierre Borgnat, Aurélien Garivier, Amaury Habrard
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs.
no code implementations • 24 Apr 2020 • Ievgen Redko, Emilie Morvant, Amaury Habrard, Marc Sebban, Younès Bennani
Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation.
no code implementations • 4 Sep 2019 • Léo Gautheron, Emilie Morvant, Amaury Habrard, Marc Sebban
A key element of any machine learning algorithm is the use of a function that measures the dis/similarity between data points.
no code implementations • 2 Sep 2019 • Rémi Viola, Rémi Emonet, Amaury Habrard, Guillaume Metzler, Sébastien Riou, Marc Sebban
In this paper, we address the challenging problem of learning from imbalanced data using a Nearest-Neighbor (NN) algorithm.
no code implementations • 14 Jun 2019 • Léo Gautheron, Pascal Germain, Amaury Habrard, Emilie Morvant, Marc Sebban, Valentina Zantedeschi
Unlike state-of-the-art Multiple Kernel Learning techniques that make use of a pre-computed dictionary of kernel functions to select from, at each iteration we fit a kernel by approximating it as a weighted sum of Random Fourier Features (RFF) and by optimizing their barycenter.
2 code implementations • Pattern Recognition Letters 2019 • Tien-Nam Le, Amaury Habrard, Marc Sebban
In unsupervised domain adaptation (DA), 1 aims at learning from labeled source data and fully unlabeled target examples a model with a low error on the target domain.
1 code implementation • 24 Mar 2018 • Julien Tissier, Christophe Gravier, Amaury Habrard
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances.
1 code implementation • EMNLP 2017 • Julien Tissier, Christophe Gravier, Amaury Habrard
Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks.
no code implementations • 17 Jul 2017 • Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), which relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter domain adaptation bound for the target risk.
2 code implementations • NeurIPS 2017 • Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy
This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function $f$ in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known.
no code implementations • NeurIPS 2016 • Michaël Perrot, Nicolas Courty, Rémi Flamary, Amaury Habrard
Most of the computational approaches of Optimal Transport use the Kantorovich relaxation of the problem to learn a probabilistic coupling $\mgamma$ but do not address the problem of learning the underlying transport map $\funcT$ linked to the original Monge problem.
no code implementations • 15 Oct 2016 • Maria-Irina Nicolae, Éric Gaussier, Amaury Habrard, Marc Sebban
In this paper, we propose a novel method for learning similarities based on DTW, in order to improve time series classification.
no code implementations • 14 Oct 2016 • Ievgen Redko, Amaury Habrard, Marc Sebban
Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different.
no code implementations • NeurIPS 2015 • Michaël Perrot, Amaury Habrard
In this paper, instead of bringing closer examples of the same class and pushing far away examples of different classes we propose to move the examples with respect to virtual points.
1 code implementation • 15 Jun 2015 • Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
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.
no code implementations • 24 Mar 2015 • Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
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 majority vote on a different target distribution.
no code implementations • 13 Jan 2015 • Pascal Germain, Amaury Habrard, Francois Laviolette, Emilie Morvant
This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory.
no code implementations • 19 Dec 2014 • Maria-Irina Nicolae, Marc Sebban, Amaury Habrard, Éric Gaussier, Massih-Reza Amini
The notion of metric plays a key role in machine learning problems such as classification, clustering or ranking.
no code implementations • 18 Sep 2014 • Basura Fernando, Amaury Habrard, Marc Sebban, Tinne Tuytelaars
We present two approaches to determine the only hyper-parameter in our method corresponding to the size of the subspaces.
no code implementations • 30 Apr 2014 • Emilie Morvant, Amaury Habrard, Stéphane Ayache
Our method is based on an order-preserving pairwise loss adapted to ranking that allows us to improve Mean Averaged Precision measure while taking into account the diversity of the voters that we want to fuse.
no code implementations • 21 Dec 2013 • François Denis, Mattias Gybels, Amaury Habrard
Existing concentration bounds seem to indicate that the concentration over $H_r$ gets looser with the size of $H_r$, suggesting to make a trade-off between the quantity of used information and the size of $H_r$.
no code implementations • 28 Jun 2013 • Aurélien Bellet, Amaury Habrard, Marc Sebban
The need for appropriate ways to measure the distance or similarity between data is ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such good metrics for specific problems is generally difficult.
no code implementations • 5 Sep 2012 • Aurélien Bellet, Amaury Habrard
Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied.
no code implementations • 27 Jun 2012 • Aurelien Bellet, Amaury Habrard, Marc Sebban
In recent years, the crucial importance of metrics in machine learning algorithms has led to an increasing interest for optimizing distance and similarity functions.