May 2025
Tutorial on PAC-Bayes Accepted at COLT 2025April 2025
Habilitation à Diriger des RecherchesNew Website
Older news
-
Advances in PAC-Bayesian theory from generalization bounds to supervised and transfer learning algorithms (in french)
- May 24: Accepted paper at ECML-PKDD 2024
A Theoretically Grounded Extension of Universal Attacks from the Attacker's Viewpoint - May 24: Accepted paper at ECML-PKDD 2024
A Theoretically Grounded Extension of Universal Attacks from the Attacker's Viewpoint - May 24: A communication accepted paper at CAp 2024
Une borne PAC-Bayésienne sur une mesure de risque pour l'apprentissage équitable - Jan 24: Accepted paper at AISTATS 2024
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures - July 23: Accepted paper a Machine Learning Journal
Included in the program of ECML-PKDD 2023
- Dec 22: Paul Viallard defended his Ph.D. Congratz !
Beyond PAC-Bayesian Bounds: From Disintegration to Novel Bounds - May 22: 2 communications accepter at CAp'22
- I was a meta-reviewer for ECML-PKDD'22
- March 22: I was an external examinator of the PhD Thesis of Luxin Zhang --- Well done
Model Agnostic Domain Adaptation: Application to Fraud Detection - I was a reviewer for ICML 2022
- Two papers accepted at NeurIPS 2021
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
A PAC-Bayes Analysis of Adversarial Robustness - I am the publicity chair of ECML-PKDD 2022
- I am a membre of CNU 27
the french National Council of Universities for computer science - June 21: A paper accepted at ECML-PKDD'21
Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
- May 21: 3 communcations accepted at CAp'21
- I was a reviewer for ICML 2021
- Dec. 20: Léo Gautheron defended his Ph.D. Well Done.
- June 20: A paper accepted at ECML-PKDD'20
Landmark-based Ensemble Learning with Random Fourier Features and Gradient Boosting
- May 20: Two communications accepted at CAp'20
- Apr. 20: A short version of our domain adaptation book is avalaible on ArXiV
Metric Learning from Imbalanced Data with Generalization Guarantees - A paper accepted in Pattern Recognition Letters
Metric Learning from Imbalanced Data with Generalization Guarantees - A communication accepted to ML with Guarantees
workshop @NeurIPS'19
Interpreting Neural Networks as Majority Votes through the PAC-Bayesian Theory - I will be a reviewer for IDA 2020
- Sept. 19: Spare time news - I obtained my 2nd star Black Belt in MKF
- Aug. 19: Our book on Domain Adaptation Theory is now available
- Aug. 19: A paper accepted in Neurocomputing journal
PAC-Bayes and Domain Adaptation - Aug. 19: A paper accepted at ICTAI'19
Metric Learning from Imbalanced Data - June 19: I am a board Member of the MALIA group of SFdS
- June 19: I will give a talk during JDS'19
When PAC-Bayesian Majority Vote meets Domain Adaptation
- May 19: One communication accepted at >CAp'19
- May 19: A paper accepted in Neurocomputing journal
- I will be a reviewer for ECML-PKDD'19
- Jan. 19: The website of our project APRIORI is online here
- Dec. 18: paper accepted at AISTATS'2019
Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior - I will be a reviewer for ICML'19
- Research report on PAC-Bayes and Random Fourier features
- Oct. 18: Congratz to my student Anil Goyal who obtained his Ph.D.
- Post-Doc offer: Machine Learning for Multiview Learning
More informations here - ANR project APRIORI accepted (I am the coordinator)
A Pac-bayesian RepresentatIOn leaRnIng perspective - A paper accepted at IDA'18
Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization - I will be the co-chair of the Demo track ECML/PKDD'19
- Two communications accepted at CAp'18
- I am a reviewer for ICML'18
- I gave a talk at INRIA Lille, MODAL team
When PAC-Bayesian Majority Vote meets Transfer Learning
- INS2I-CNRS project JCJC 2018 accepted "PaRaFF" (with P. Germain)
PAC-Bayesian Random Fourier Features
- I will be a member of the scientific comittee of a NIPS 2017 workshop
(Almost) 50 Shades of Bayesian Learning: PAC-Bayesian trends and insights - Post-Doc offer: Machine Learning for Multiview Learning
More informations here - I am one of the vice-president of the SSFAM
The French Association on Machine Learning
- June 17: A paper accepted at ECML'17
PAC-Bayesian Analysis for a two-step Hierarchical Mutliview Learning Approach
- May 17: A communication accepted at CAp'17
- I will be a reviewer for NIPS'17
- I will be a reviewer for ICML'17
- Spare-time news: I am a 1st Star Black Belt in Mansuria Kung Fu!!
- The Hubert Curien Lab has its own Facebook Page
and Twitter account Follow @LabHubertCurien - My research group has its own YouTube Channel!
Follow us
- Sept 16: A paper accepted in Neurocomputing
Risk Upper Bounds for General Ensemble Methods with an application to Multiclass Classification
- May 16: A paper accepted at CAp 2016
The french conference on machine learning - April 16: A paper accepted at ICML 2016
- March 16: A new version of the research report
A New PAC-Bayesian Perspective on Domain Adaptation
- My research group has its own Twitter account! Follow @DataIntelGroup
- What is Domain Adaptation?---a popularization: Slides of a talk I gave (in french)
- I will be a I will be a member of the programm comittee of BeyondLabeler - Human is More Than a Labeler
- I'm responsible of the maintenance & development of LabMetry (bibliometry platform created by J. Bennegent & F. Voron)
- The source code of our new domain adapatation algo is available here
- A communication accepted at a NIPS'15 Workshop
Transfer and Multi-Task Learning: Trends and New Perspectives - I am a member of the program comittee of the french conference on machine learning (CAp'16)
- I will be a reviewer for ICML 2016
- I am a member of the board of the Hubert Curien Lab.
- I was a reviewer for TASK-CV 2015
- I'm in charge of the 2nd year of BSc in Computer Science
- June 15: The research report on our novel work on domain adaptation is available
A new PAC-Bayesian perspective on Domain Adaptation - June 15: A new version of the research report
On the Generalization of the C-Bound to Structured Output Ensemble Methods - April 15: We are opening a PhD thesis position
Annotations transfer in a domain adaptation framework - Mar 15: Our long paper on PAC-Bayesian theorems for domain adaptation is available on arXiv
- Reviewer for ICML'2015
- Two communications accepted at NIPS'14 Workshops
Transfer and Multi-task learning: Theory Meets Practice
Representation and Learning Methods for Complex Outputs
- I will be a member of the organization committe of IDA 2015
(International Symposium on Intelligent Data Analysis) - Oct 14: I am an assitant professor at university of Saint-Etienne
- Sept 14: I received a Ph.D. award from Aix-Marseille Univ.
- A paper accepted at NIPS'14
- A paper accepted to Pattern Recognition Letters
- A paper accepted to Machine Learning Journal
in the ECML/PKDD 2014 journal track
- A paper accepted at CAp 2014
The french conference on machine learning - May 14: My Ph.D. is awarded with a 1st accessit
of the "Prix de thèse de l'AFIA 2014"
- April 14: A paper accepted at S+SSPR 14
- I will co-organize LEMA a workshop at ECML-PKDD'14
LEarning with Multiple views: Applications to computer vision and multimedia
- A communication accepted at a NIPS'13 Workshop
Transfer and Multi-Task Learning Workshop
- A communication accepted at WiML'13
Women in Machine Learning workshop
- I will be a co-chair of ÖAGM 2014
(The Annual Workshop of the Austrian Association for Pattern Recognition)
-
1st Oct. 13: I am a postdoc at the IST Austria
-
Sept. 13: A paper accepted at ACML 2013
-
18 Sept. 13: Ph.D. public defense
-
April 13: Two papers accepted at CAp'13
(French Conference on ML)
- March 13: A paper accepted at ICML 2013