Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Amaury Habrard

Amaury Habrard

LHC

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


Jun 23, 2021
Valentina Zantedeschi, Paul Viallard, Emilie Morvant, RĂ©mi Emonet, Amaury Habrard, Pascal Germain, Benjamin Guedj

Figure 1 for Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
Figure 2 for Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
Figure 3 for Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
Figure 4 for Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound

  Access Paper or Ask Questions

Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound


Apr 28, 2021
Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

Figure 1 for Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
Figure 2 for Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
Figure 3 for Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
Figure 4 for Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound

  Access Paper or Ask Questions

A PAC-Bayes Analysis of Adversarial Robustness


Feb 19, 2021
Guillaume Vidot, Paul Viallard, Amaury Habrard, Emilie Morvant

Figure 1 for A PAC-Bayes Analysis of Adversarial Robustness
Figure 2 for A PAC-Bayes Analysis of Adversarial Robustness
Figure 3 for A PAC-Bayes Analysis of Adversarial Robustness

  Access Paper or Ask Questions

A General Framework for the Derandomization of PAC-Bayesian Bounds


Feb 17, 2021
Paul Viallard, Pascal Germain, Amaury Habrard, Emilie Morvant

Figure 1 for A General Framework for the Derandomization of PAC-Bayesian Bounds

  Access Paper or Ask Questions

Multiview Variational Graph Autoencoders for Canonical Correlation Analysis


Oct 30, 2020
Yacouba Kaloga, Pierre Borgnat, Sundeep Prabhakar Chepuri, Patrice Abry, Amaury Habrard

Figure 1 for Multiview Variational Graph Autoencoders for Canonical Correlation Analysis
Figure 2 for Multiview Variational Graph Autoencoders for Canonical Correlation Analysis
Figure 3 for Multiview Variational Graph Autoencoders for Canonical Correlation Analysis
* 4 pages, 3 figures, submitted 
  Access Paper or Ask Questions

Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms


Oct 05, 2020
Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard

Figure 1 for Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
Figure 2 for Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
Figure 3 for Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
Figure 4 for Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms

  Access Paper or Ask Questions

Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening


Jul 07, 2020
Louis Béthune, Yacouba Kaloga, Pierre Borgnat, Aurélien Garivier, Amaury Habrard

Figure 1 for Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
Figure 2 for Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
Figure 3 for Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
Figure 4 for Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
* 17 pages, 15 figures, submitted 
  Access Paper or Ask Questions

A survey on domain adaptation theory


Apr 24, 2020
Ievgen Redko, Emilie Morvant, Amaury Habrard, Marc Sebban, Younès Bennani

Figure 1 for A survey on domain adaptation theory
Figure 2 for A survey on domain adaptation theory
Figure 3 for A survey on domain adaptation theory
Figure 4 for A survey on domain adaptation theory

  Access Paper or Ask Questions

Metric Learning from Imbalanced Data


Sep 04, 2019
LĂ©o Gautheron, Emilie Morvant, Amaury Habrard, Marc Sebban

Figure 1 for Metric Learning from Imbalanced Data
Figure 2 for Metric Learning from Imbalanced Data
Figure 3 for Metric Learning from Imbalanced Data
Figure 4 for Metric Learning from Imbalanced Data

  Access Paper or Ask Questions

An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data


Sep 02, 2019
RĂ©mi Viola, RĂ©mi Emonet, Amaury Habrard, Guillaume Metzler, SĂ©bastien Riou, Marc Sebban

Figure 1 for An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
Figure 2 for An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
Figure 3 for An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
Figure 4 for An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
* In Proceedings of the 31 International Conference on Tools with Artificial Intelligence (ICTAI 2019) 
  Access Paper or Ask Questions

Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting


Jun 14, 2019
LĂ©o Gautheron, Pascal Germain, Amaury Habrard, Emilie Morvant, Marc Sebban, Valentina Zantedeschi

Figure 1 for Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting
Figure 2 for Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting
Figure 3 for Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting
Figure 4 for Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting

  Access Paper or Ask Questions

Near-lossless Binarization of Word Embeddings


May 28, 2018
Julien Tissier, Amaury Habrard, Christophe Gravier

Figure 1 for Near-lossless Binarization of Word Embeddings
Figure 2 for Near-lossless Binarization of Word Embeddings
Figure 3 for Near-lossless Binarization of Word Embeddings
Figure 4 for Near-lossless Binarization of Word Embeddings

  Access Paper or Ask Questions

Joint Distribution Optimal Transportation for Domain Adaptation


Oct 22, 2017
Nicolas Courty, RĂ©mi Flamary, Amaury Habrard, Alain Rakotomamonjy

Figure 1 for Joint Distribution Optimal Transportation for Domain Adaptation
Figure 2 for Joint Distribution Optimal Transportation for Domain Adaptation
Figure 3 for Joint Distribution Optimal Transportation for Domain Adaptation
Figure 4 for Joint Distribution Optimal Transportation for Domain Adaptation
* Accepted for publication at NIPS 2017 
  Access Paper or Ask Questions

Theoretical Analysis of Domain Adaptation with Optimal Transport


Jul 28, 2017
Ievgen Redko, Amaury Habrard, Marc Sebban

Figure 1 for Theoretical Analysis of Domain Adaptation with Optimal Transport

  Access Paper or Ask Questions

PAC-Bayes and Domain Adaptation


Jul 17, 2017
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Figure 1 for PAC-Bayes and Domain Adaptation
Figure 2 for PAC-Bayes and Domain Adaptation
Figure 3 for PAC-Bayes and Domain Adaptation
Figure 4 for PAC-Bayes and Domain Adaptation
* arXiv admin note: text overlap with arXiv:1503.06944 
  Access Paper or Ask Questions

Similarity Learning for Time Series Classification


Oct 15, 2016
Maria-Irina Nicolae, Éric Gaussier, Amaury Habrard, Marc Sebban

Figure 1 for Similarity Learning for Time Series Classification
Figure 2 for Similarity Learning for Time Series Classification
Figure 3 for Similarity Learning for Time Series Classification
Figure 4 for Similarity Learning for Time Series Classification
* Techreport 
  Access Paper or Ask Questions

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers


Aug 09, 2016
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Figure 1 for PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
Figure 2 for PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
Figure 3 for PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
Figure 4 for PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
* This report is a long version of our paper entitled A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers published in the proceedings of the International Conference on Machine Learning (ICML) 2013. We improved our main results, extended our experiments, and proposed an extension to multisource domain adaptation 
  Access Paper or Ask Questions

A New PAC-Bayesian Perspective on Domain Adaptation


Jul 26, 2016
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Figure 1 for A New PAC-Bayesian Perspective on Domain Adaptation
Figure 2 for A New PAC-Bayesian Perspective on Domain Adaptation
Figure 3 for A New PAC-Bayesian Perspective on Domain Adaptation
* Published at ICML 2016 
  Access Paper or Ask Questions

Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions


Mar 31, 2015
Maria-Irina Nicolae, Marc Sebban, Amaury Habrard, Éric Gaussier, Massih-Reza Amini

Figure 1 for Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
Figure 2 for Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
Figure 3 for Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
Figure 4 for Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
* ICLR 2015 Workshop - accepted 
  Access Paper or Ask Questions

An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context


Jan 13, 2015
Pascal Germain, Amaury Habrard, Francois Laviolette, Emilie Morvant

* NIPS 2014 Workshop on Transfer and Multi-task learning: Theory Meets Practice, Dec 2014, Montr{\'e}al, Canada 
  Access Paper or Ask Questions

Subspace Alignment For Domain Adaptation


Oct 23, 2014
Basura Fernando, Amaury Habrard, Marc Sebban, Tinne Tuytelaars

Figure 1 for Subspace Alignment For Domain Adaptation
Figure 2 for Subspace Alignment For Domain Adaptation
Figure 3 for Subspace Alignment For Domain Adaptation
Figure 4 for Subspace Alignment For Domain Adaptation

  Access Paper or Ask Questions

Robustness and Generalization for Metric Learning


Sep 29, 2014
Aurélien Bellet, Amaury Habrard

Figure 1 for Robustness and Generalization for Metric Learning
* Neurocomputing,151(1):259-267, 2015 
 * 16 pages, to appear in Neurocomputing 
  Access Paper or Ask Questions

Majority Vote of Diverse Classifiers for Late Fusion


Jun 19, 2014
Emilie Morvant, Amaury Habrard, Stéphane Ayache

Figure 1 for Majority Vote of Diverse Classifiers for Late Fusion
Figure 2 for Majority Vote of Diverse Classifiers for Late Fusion
Figure 3 for Majority Vote of Diverse Classifiers for Late Fusion
* IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recignition, Joensuu : Finland (2014) 
  Access Paper or Ask Questions

A Survey on Metric Learning for Feature Vectors and Structured Data


Feb 12, 2014
Aurélien Bellet, Amaury Habrard, Marc Sebban

Figure 1 for A Survey on Metric Learning for Feature Vectors and Structured Data
Figure 2 for A Survey on Metric Learning for Feature Vectors and Structured Data
Figure 3 for A Survey on Metric Learning for Feature Vectors and Structured Data
Figure 4 for A Survey on Metric Learning for Feature Vectors and Structured Data
* Technical report, 59 pages. Changes in v2: fixed typos and improved presentation. Changes in v3: fixed typos. Changes in v4: fixed typos and new methods 
  Access Paper or Ask Questions

Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning


Dec 21, 2013
François Denis, Mattias Gybels, Amaury Habrard

Figure 1 for Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
Figure 2 for Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
Figure 3 for Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
Figure 4 for Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
* Extended version of a paper to appear at ICML 2014 
  Access Paper or Ask Questions

PAC-Bayesian Learning and Domain Adaptation


Dec 11, 2012
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Figure 1 for PAC-Bayesian Learning and Domain Adaptation
Figure 2 for PAC-Bayesian Learning and Domain Adaptation
* Multi-Trade-offs in Machine Learning, NIPS 2012 Workshop, Lake Tahoe : United States (2012) 
 * https://sites.google.com/site/multitradeoffs2012/ 
  Access Paper or Ask Questions

PAC-Bayesian Majority Vote for Late Classifier Fusion


Jul 04, 2012
Emilie Morvant, Amaury Habrard, Stéphane Ayache

Figure 1 for PAC-Bayesian Majority Vote for Late Classifier Fusion
* 7 pages, Research report 
  Access Paper or Ask Questions

Similarity Learning for Provably Accurate Sparse Linear Classification


Jun 27, 2012
Aurelien Bellet, Amaury Habrard, Marc Sebban

Figure 1 for Similarity Learning for Provably Accurate Sparse Linear Classification
Figure 2 for Similarity Learning for Provably Accurate Sparse Linear Classification
Figure 3 for Similarity Learning for Provably Accurate Sparse Linear Classification
Figure 4 for Similarity Learning for Provably Accurate Sparse Linear Classification
* Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 
  Access Paper or Ask Questions

Using Pseudo-Stochastic Rational Languages in Probabilistic Grammatical Inference


Nov 07, 2008
Amaury Habrard, Francois Denis, Yann Esposito

Figure 1 for Using Pseudo-Stochastic Rational Languages in Probabilistic Grammatical Inference
Figure 2 for Using Pseudo-Stochastic Rational Languages in Probabilistic Grammatical Inference
Figure 3 for Using Pseudo-Stochastic Rational Languages in Probabilistic Grammatical Inference
Figure 4 for Using Pseudo-Stochastic Rational Languages in Probabilistic Grammatical Inference
* 8th International Colloquium on Grammatical Inference (ICGI'06), Japan (2006) 
  Access Paper or Ask Questions

On Probability Distributions for Trees: Representations, Inference and Learning


Jul 18, 2008
François Denis, Amaury Habrard, Rémi Gilleron, Marc Tommasi, Édouard Gilbert

* Dans NIPS Workshop on Representations and Inference on Probability Distributions (2007) 
  Access Paper or Ask Questions