Here are only reported talks given in English. If you are also interested in my French talks, please go to the French version of this page.
Organisation
- 2013/06/05--07 - Second Workshop on Industry & Practices for Forecasting (WIPFOR), EDF R&D, Clamart. Program Committee member.
International conferences and workshops
- 2013/03/20 - Fête Parisienne in Computation, Inference and Optimization: A Young Researchers' Forum, IHES.
Optimal model selection with V-fold cross-validation: how should V be chosen?
[abstract]
[slides]
- 2013/01/21 - Non-stationarity in Statistics and Risk Management, CIRM, Luminy.
Kernel change-point detection [abstract]
[slides]
- 2012/07/09 - World Congress in Probability and Statistics 2012, Istanbul.
Optimal model selection with V-fold cross-validation: how should V be chosen? [abstract]
[slides]
- 2012/03/08 - Inaugural Conference of the Laboratory Fibonacci, Scuola Normale Superiore di Pisa.
Resampling-based estimation of the accuracy of satellite ephemerides
[abstract]
[slides]
- 2011/08/30 - MCP 2011
Resampling-based confidence regions and multiple tests
[slides]
[abstract]
- 2010/03/29 - Workshop "Modern Nonparametric Statistics: Going Beyond Asymptotic
Minimax", MFO, Oberwolfach, Germany
Data-driven penalties for linear estimator selection
[slides]
[abstract]
- 2010/01/29 - Workshop on Challenging
problems in statistical learning, Paris.
Data-driven penalties for optimal calibration of learning algorithms
[slides]
[abstract]
[video]
- 2009/07/23 -
European Meeting of Statisticians,
Toulouse. Statistical learning session.
Optimal model selection
[slides]
[abstract]
- 2008/09/02 - Statistical Mathematics and Applications, Fréjus, France
Data-driven calibration of penalties for least squares regression
[slides]
[abstract]
- 2008/06/18 - Journées
Statistiques du Sud, INSA, Toulouse, France
V-fold cross-validation improved: V-fold penalization
[slides]
[abstract]
- 2008/06/05 - Second Congress Canada-France, Université du Québec à Montréal, Montréal, Canada.
V-fold penalization: an alternative to V-fold cross-validation
[slides]
[abstract]
- 2008/03/26 - Cherry Bud Workshop 2008, Keio University, Yokohama, Japon
V-fold penalization: an alternative to V-fold cross-validation
[slides]
[abstract]
- 2007/10/26 - Workshop "Reassessing the paradigms of statistical
model-building", MFO, Oberwolfach,
Germany
V-fold penalization: an alternative to V-fold
cross-validation [slides]
[extended abstract] [abstract]
- 2007/06/13 - COLT 2007, San Diego, Californie, USA.
Resampling-based confidence regions and multiple tests for a correlated random vector [slides]
- 2007/05/16 - Pascal workshop and Pascal challenge Type I and type II errors for Multiple
Simultaneous Hypothesis Testing, Paris 5.
Resampling-based confidence regions and multiple tests for a correlated random vector [slides] [video]
- 2006/11/14 -
Mathematical Statistics and Applications, CIRM, Marseille-Luminy.
Model selection in regression with resampling penalties
[slides]
Seminars
- 2011/11/04 - Statistics Seminar, University of Cambridge.
Data-driven calibration of linear estimators with minimal penalties, with an application to multi-task regression
[slides]
[abstract]
- 2009/11/05 - Scuola Normale Superiore di Pisa
Resampling-based estimation of the accuracy of satellite ephemerides
[slides]
[abstract]
- 2009/11/03 - Università degli Studi di
Siena, Dipartimento di Ingegneria dell'Informazione
Study of the Yoccoz-Birkeland model
[slides]
[abstract]
[video 1: 3d bifurcation diagram]
[video 2: orbit on the attractor]
[video 3: stability of the fold]
- 2009/04/22 - Mathematical
Statistics Seminar, Weierstrass Institute, Berlin
Data-driven penalties for model selection
[slides]
[abstract]
- 2008/03/17 - Bin
Yu's research group meeting, Statistics Department, UC Berkeley, CA, USA
V-fold cross-validation improved: V-fold penalization
[slides]
[abstract]
- 2008/02/07 - CIS Seminar, Computer Science Department, UC Berkeley, CA, USA
V-fold penalization: an alternative to V-fold cross-validation
[slides]
[abstract]
- 2007/11/06 - TAO Seminar, LRI, Orsay
V-fold penalization: an alternative to V-fold cross-validation
[slides]
[abstract]
Other talks
- 2006/07/08 - Probability Summer School, Saint-Flour (Cantal, France).
Model selection by resampling penalization
[slides]
Back to index