Nicolas Vayatis - Publications (by topic)

BACK TO MAIN PAGE

Predictive Modeling: Ranking and scoring

N. Vayatis
Applications of concentration inequalities for statistical scoring and ranking problems
ESAIM: PROCEEDINGS, Vol. 44, p. 99-109
, January 2014.

S. Clémençon, M. Depecker, and N. Vayatis.
Ranking Forests.
(PDF)
Journal of Machine Learning Research.
Volume 14(Jan):39-73, 2013.

S. Clémençon, S. Robbiano, and N. Vayatis.
Ranking data with ordinal labels: optimality and pairwise aggregation.
(PDF)
Machine Learning.
Volume 91(1): 67-104, 2013.

S. Clémençon, M. Depecker, and N. Vayatis.
An empirical comparison of learning algorithms for nonparametric scoring. The TreeRank algorithm and other methods.

Pattern Analysis and Applications, 2012.

S. Clémençon, M. Depecker, and N. Vayatis.
Adaptive partitioning schemes for bipartite ranking.

Machine Learning Journal
. Vol. 83(1): 31-69, 2011.

S. Clémençon, M. Depecker, and N. Vayatis.
Nonparametric scoring methods as a support decision tool for medical diagnosis.

Proceedings of the Workshop on Knowledge Discovery in Health Care and Medicine at ECML-KDD'2011, 2011.

S. Clémençon and N. Vayatis.
Overlaying classifiers: A practical approach for optimal scoring.

Constructive Approximation
. Vol. 32(3):619-648, 2010.

N. Baskiotis, S. Clémençon, M. Depecker, and N. Vayatis.
TreeRank: an R package for bipartite ranking.

Proceedings of SMDTA 2010 - Stochastic Modeling Techniques and Data Analysis International Conference, June 2010.

S. Clémençon, M. Depecker, and N. Vayatis.
Données avec label binaire : avancées récentes dans le domaine de l'apprentissage statisticque d'ordonnancements.

CAP 2010 - conférence Francophone sur l'Apprentissage Automatique. Mai 2010.
Prix du meilleur article de la conférence. Paru dans RFIA, Vol.5, n°.3:345-368 (2011).

S. Clémençon, M. Depecker, and N. Vayatis.
Bagging ranking trees.

Proceedings of IEEE-ICMLA'09, pp.658-663, 2009.

S. Clémençon, M. Depecker, and N. Vayatis.
AUC maximization and the two-sample problem.

Proceedings of NIPS'09, Advances in Neural Information Processing Systems 22, pp.360-368, MIT Press, 2009.

S. Clémençon and N. Vayatis.
Adaptive estimation of the optimal ROC curve and a bipartite ranking algorithm.

Proceedings of ALT'09. Lecture Notes in Computer Science 5809, pp. 216-231, Springer, 2009.

S. Clémençon and N. Vayatis.
On partitioning rules for bipartite ranking.

Proceedings, of AISTATS'09,  Journal of Machine Learning Research, vol.5:89-96, 2009.

S. Clémençon and N. Vayatis.
Nonparametric estimation of the Precision-Recall curve.

Proceedings of ICML'09, L. Bottou and M. Littman (eds), p.185-192, Omnipress, Montreal, 2009.

S. Clémençon and N. Vayatis.
Tree-based ranking methods.

IEEE Transactions on Information Theory. Vol. 55(9):4316-4336, 2009.

S. Clémençon and N. Vayatis.
Empirical performance maximization for linear rank statistics.

Proceedings of NIPS'08, Advances in Neural Information Processing Systems 21, pp. 305-312, MIT Press, 2008.

S. Clémençon and N. Vayatis.
Overlaying classifiers: a practical approach for optimal scoring.

Proceedings of NIPS'08, Advances in Neural Information Processing Systems 21, pp.313-320, MIT Press, 2008.

P. Bertail, S. Clémençon and N. Vayatis.
On bootstrapping the ROC curve.

Proceedings of NIPS'08, Advances in Neural Information Processing Systems 21, pp.137-144, MIT Press, 2008.

S. Clémençon and N. Vayatis.
Tree-structured ranking rules and approximation of the optimal ROC curve.

Proceedings of ALT'08, 2008.

S. Clémençon, G. Lugosi, and N. Vayatis.
Ranking and empirical risk minimization of U-statistics.

The Annals of Statistics
, vol.36(2):844-874, 2008.

S. Clémençon and  N. Vayatis.
Ranking the best instances.

Journal of Machine Learning Research
, 8(Dec):2671-2699, 2007.

S. Clémençon, G. Lugosi, and N. Vayatis.
Discussion on the 2004 IMS Medallion Lecture "Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii.

The  Annals of Statistics
, 34(6):2672-2676, 2006.

S. Clémençon, G. Lugosi, and N.Vayatis.
Ranking and scoring using empirical risk minimization.

Proceedings of COLT 2005
, in LNCS Computational Learning Theory, vol. 3559, pp.1--15, Springer, 2005.

S. Clémençon, G. Lugosi, and N.Vayatis.
From Ranking to Classification: a Statistical View.
Proceedings of the 29th Annual Conference of the German Classification Society (GfKl 2005)
, University of Magdeburg, 2005.

Learning from Graphs

Kevin Scaman, Argyris Kalogeratos, Nicolas Vayatis.
What Makes a Good Plan? An Efficient Planning Approach to Control Diffusion Processes in Networks.
arXiv:1407.4760, 17 Jul 2014

Rémi Lemonnier, Kevin Scaman, Nicolas Vayatis.
Tight Bounds for Influence in Diffusion Networks and Application to Bond Percolation and Epidemiology.
Proceedings of NIPS'14

K. Scaman, A. Kalogeratos, N. Vayatis.
Dynamic Treatment Allocation for Epidemic Control in Arbitrary Networks. (PDF)
Proceedings of WSDM 2014 Diffusion in Networks and Cascade Analytics (DiffNet) Workshop, February, NYC, 2014.

E. Richard, S. Gaiffas, and N. Vayatis.
Link Prediction in Graphs with Autoregressive Features. (PDF)
Journal of Machine Learning Research.
Volume 15(Feb):565−593, 2014.

E. Richard, A. Argyriou, T. Evgeniou, N. Vayatis.
A Regularization Approach for Prediction of Edges and Node Features in Dynamic Graphs.

arXiv:1203.5438
, 2013.

E. Richard, P.A. Savalle, and N. Vayatis.
Estimating simultaneously sparse and low-rank matrices.
  (PDF)
Proceedings of ICML'12, 2012

E. Richard, S. Gaiffas, and N. Vayatis.
Link Prediction in Graphs with Autoregressive Features.
(PDF)
Proceedings of NIPS'12, 2012.

E. Richard,D. Buffoni, N. Baskiotis, and N. Vayatis.
Taking the best of many link recommendations and applications to C2C e-commerce.

Preprint, 2012.

E. Richard, N. Baskiotis, T. Evgeniou, and N. Vayatis.
Link discovery using Graph Feature Tracking.

Proceedings of NIPS'10, Advances in Neural Information Processing Systems 23, MIT Press, 2010.


Sequential optimization and experimental design

E. Contal, and N. Vayatis.
Gaussian Process Optimization with Mutual Information.
arXiv:1311.4825
, 2014.

E. Contal, D. Buffoni, A. Robicquet, and N. Vayatis.
Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration
. (PDF)(Software).
Proceedings of ECML, Prague, 2013.


Applications to Engineering and Physics

S. Varet, P. Dossantos-Uzarralde, N. Vayatis and E. Bauge.
A method using Pseudo-measurements and shrinkage for the estimation of cross section covariances.
Nuclear Data Sheets, 118, p.357-359, 2014. 

S. Varet, P. Dossantos-Uzarralde, N. Vayatis.
A statistical approach for experimental cross-section covariances estimation via shrinkage.
Nuclear Science and Engineering, Accepted, 2014.

S. Varet, P. Dossantos-Uzarralde, N. Vayatis.
Quality quantification of evaluated cross section covariances.
Proceedings of the CW2014 workshop, 2014. 

S. Varet, P. Dossantos-Uzarralde, N. Vayatis.
Uncertainty estimation of nuclear interaction description from a model hierarchy.
Proceedings of the Uncertainties 2014 Conference, 2014.

G. Merle, J.-M. Roussel, V. Perchet, J.-J. Lesage and N. Vayatis.
Quantitative analysis of Dynamic Fault Trees based on the coupling of structure functions ure functions and Monte-Carlo simulation.

Quality and Reliability Engineering International. Accepted, 2014.

J. Costes, J.-M. Ghidaglia, P. Muguerra, K. L. Nielsen, X. Riou, J.-P. Saut, and N. Vayatis.
On the Simulation of Offshore Oil Facilities at the System Level. (PDF)
Proceedings of the 10th International Modelica Conference, 2014.

T.S. Stefanakis, E. Contal, N. Vayatis, F. Dias, and C. E. Synolakis.
Can Small Islands Protect Nearby Coasts From Tsunamis? An Active Experimental Design Approach
.
arXiv:1305.7385. Proceeding of the Royal Society-A, Accepted, 2014.

F. Dias, S. Guillas, N. Vayatis, A. Sarri, T. S. Stefanakis, E. Contal and C. E. Synolakis
.
New methods for sensitivity analysis and uncertainty quantification of tsunamis. (PDF)
Proceedings of the 14th Asia Congress of Fluid Mechanics, Hanoi and Halong, Vietnam.

S. Varet, P. Dossantos-Uzarralde, N. Vayatis,  E. Bauge
Pseudo-measurement simulations and shrinkage for the experimental cross-section covariances optimisation.
Proceedings of the International Conference on Nuclear Data for Science and Technology,  NYC.

P. Dossantos-Uzarralde,  N. Vayatis, S. Varet
Statistical selection of numerical models with deterministic parameters for cross-section uncertainty evaluations.
Proceedings of the International Conference on Nuclear Data for Science and Technology, NYC.

A. Dematteo, S. Clémençon, N. Vayatis, M. Mougeot.
Sloshing in the LNG shipping industry: risk modelling through multivariate heavy-tail analysis.
arXiv:1312.0020, 2013.

T.S. Stefanakis, F. Dias, N. Vayatis, and S. Guillas.
Long-Wave Runup On A Plane Beach Behind A Conical
Island.
Proceedings of 15 WCEE, Lisboa, 2012.

S. Varet, P. Dossantos-Uzarralde, N. Vayatis, and E. Bauge.
Pseudo-measurement simulations and bootstrap for the experimental cross-section covariances estimation with quality qualification.

Wonder 2012: 3rd International Workshop on Nuclear Data Evaluation for Reactor Applications (Aix-en-Provence), 2012.

S. Varet, A. Garlaud, P. Dossantos-Uzarralde, N. Vayatis, and E. Bauge.
Kriging approach for the experimental cross-section covariances estimation.

Wonder 2012: 3rd International Workshop on Nuclear Data Evaluation for Reactor Applications (Aix-en-Provence), 2012.

S. Varet, P. Dossantos-Uzarralde, N. Vayatis, R. Brault, and E. Bauge.
Experimental Covariances Contributions to Evaluated Cross Section Uncertainty Determination.

Proceedings of the Second Workshop on Neutron Cross Section Covariances, Vienna, 2011.

G. Merle, J.M. Roussel, J.J Lesage, and N. Vayatis.
Analytical Calculation of Failure Probabilities in Dynamic Default Trees including Spare Gates.

Proceedings of ESREL 2010 - European Safety a& Reliability Conference. September 2010.


Boosting

G. Lugosi and N. Vayatis.
On the Bayes-risk consistency of regularized boosting methods (with discussion).

The Annals of Statistics
, 32(1):30-55.

G. Lugosi and N. Vayatis.

Rejoinder on Three Boosting Papers.
The Annals of Statistics
, 32(1):124-127.

G. Blanchard, G. Lugosi and N. Vayatis.
On the rate of convergence of regularized boosting methods.
Journal of Machine Learning Research
, 4(Oct):861-894.

G. Lugosi and N. Vayatis.
A consistent strategy for boosting algorithms.
Proceedings of COLT'2002, University of Sidney, Australia, 2002.


Vapnik-Chervonenkis theory

N. Vayatis.
Exact Rates in Vapnik-Chervonenkis Bounds.
Annales de l'Institut Henri Poincaré (B) - Probabilités et Statistiques
, 39(1):95-119, 2003.

R. Azencott and N. Vayatis.
Refined Exponential Rates in Vapnik-Chervonenkis Inequalities.
Comptes Rendus de l'Académie des Sciences de Paris
, t.332, série I, p.563-568, 2001.

N. Vayatis.
The Role of Critical Sets in Vapnik-Chervonenkis Theory.

Proceedings of COLT'2000
, Stanford University, 2000.


Mirror descent algorithms

A. Juditsky, A. Nazin, A. Tsybakov, and N. Vayatis.
Gap-free bounds for stochastic multi-armed bandit.

Proceedings of IFAC'08
, Seoul, Korea, 2007.

A. Juditsky, A. Nazin, A. Tsybakov, and N. Vayatis.
Recursive Aggregation of Estimators via the  Mirror Descent Algorithm with averaging.

Problems of Information Transmission
,  41(4): 368-384, 2005.

A. Juditsky, A. Nazin, A. Tsybakov and N. Vayatis.

Generalization Error Bounds for Aggregation by Mirror Descent With Averaging.

Proceedings of Neural Information Processing Systems NIPS'2005
, MIT Press, 2005.


Various

A. Kohatsu-Higa, N. Vayatis, and K. Yasuda 
Strong Consistency of the Bayesian Estimator for the Ornstein–Uhlenbeck Process.
Book Chapter in Y. Kabanov, M. Rutkowski, T. Zariphopoulou (eds.), Inspired by Finance - The Musiela Festschrift: 411-437, 2014.

A. Kohatsu, N. Vayatis, and K. Yasuda.
Strong consistency of Bayesian estimator under discrete observations and unknown transition density.

in Stochastic Analysis with Financial Applications: Hong Kong 2009, A. Kohatsu-Higa, N. Privault, S.-J. Sheu eds., Birkhauser, pp. 145-168, 2011.

A. Kohatsu-Higa, N. Vayatis, and K. Yasuda.
Strong consistency of the Bayesian estimator for the Ornstein-Uhlenbeck process.

Proceedings of the Metabief Conference, 2011.

J. Defretin, S. Herbin, G. Le Besnerais, and N. Vayatis.
Adaptive Planification in Active 3D Object Recognition for Many Classes of Objects.

RSS 2010 Workshop - Robotics, Science and Systems. June 2010.

O. Ambrym-Maillard and N. Vayatis.
Complexity versus agreement for many views.

Proceedings of ALT'09, Lecture Notes in Computer Science, pp. 232-246, Springer, 2009.


 BACK TO MAIN PAGE