Journal Preprints

• Costa M. & Klein T. & Gadat, S. Black mirror: a stochastic algorithm for Sobol indices recovery. In progress.
• Dieuleveut, A. & Fort, G. & Gadat, S. & Moulines, E. GMM learning with Stochastic mirror descent. In progress.
• Crespo, M. Discretisation of Langevin diffusion in the weak log-concave case. Submitted.
• De Castro Y. & Gadat S. & Marteau C. FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures. Submitted.
  
• Gadat, S & Villeneuve, S Wasserstein geometry of information retrieval (2023). Working Paper.
• Gadat S. &  Panloup F. & Pellegrini C. On the cost of Bayesian posterior mean strategy for log-concave models (2022). Submitted.

Journal Publications

2024

• Crespo M. & Gadat S. & Gendre X.   Stochastic Langevin Monte Carlo for (weakly) log-concave posterior distributions (2024). Electronic Journal of Probability, to appear.
  
• Doury, A. & Somot, S. & Gadat, S. On the suitability of a Convolutional Neural Network based RCM-Emulator for fine spatio-temporal precipitation. Climate and Dynamics, to appear.
• Lalanne, C. & Gadat, S.Privately Learning Smooth Distributions on the Hypercube by Projections. ICML.

 

2023

• Costa M. & Huang L. & Gadat S. CV@R penalized portfolio optimization with biased stochastic mirror descent(2022). Finance and Stochastics,  to appear.
• Rey-Barroso J. & Munaretto A. & Rouquié N. & Mougel A. & Chassan M. & Gadat S & Frause F. & Dewingle O. & Cadot S. & Quillet-Mary A & Ysebaert L. & Dupré L. Multifaceted modulation of motility properties in leukemic and non-leukemic lymphocytes upon ibrutinib treatment of chronic lymphocytic leukemia. (2022). Haematologica.

2022

• Gadat, S. & Gavra, I. Asymptotic study of stochastic adaptive algorithm in non-convex landscape (2022). Journal of Machine Learning Research.
• Gadat S. &  Panloup F.  Optimal non-asymptotic bound of the Ruppert-Polyak averaging without strong convexity (2022). Stochastic Processes and their Applications.
  
• Doury A. & Somot S. & Gadat, S. & Ribes, A. & Corre, L. Regional Climate Model emulator based on deep learning: concept and first evaluation of a novel hybrid downscaling approach (2022). Climate and Dynamics.
• Bercu B & Bigot J.  & Gadat, S. & Siviero, E. A stochastic Gauss-Newton algorithm for regularized semi-discrete optimal transport (2022). Information and Inference: A Journal of the IMA, to appear.

2021

• Costa M. & Gadat S. Non-asymptotic study of a recursive superquantile estimation algorithm (2021). Electronic Journal of Statistics, 15 (2) 4718-4769.
  
• Bercu B & Costa M. & Gadat S. Stochastic approximation algorithms for superquantiles estimation (2021). Electronic Journal of Probability, 26 (84) 1-26.
  
• Lafouresse, F. & Jugele R. & Müller S. & Doineau M. & Duplan-Eche V. & Espinosa E. & Puissegur, M.P. & Gadat S & Valitutti S. Stochastic asymmetric repartition of lytic machinery in dividing human CD8+ T cells generates heterogeneous killing behaviour (2021) eLife, 10:e62691 doi: 10.7554/eLife.62691.
• De Castro Y. & Gadat S. & Marteau C. & Maugis C. SuperMix: Sparse Regularization for Mixture (2021) Annals of Statistics,49 (3) 1779 – 1809.

2020

• Gadat S. & Gerchinovitz S. & Marteau C.  Optimal functional supervised classification with separation condition (2020) Bernoulli, Volume 26, Number 3, 1797–1831.
• Gadat S. & Kahn J. &  Marteau C. & Maugis C.  Parameter recovery in two-component contamination mixtures: the L2 strategy. (2020) Annales de l’Institut Henri Poincaré (B), Volume 56, Number 2, 1391–1418.

2019

• Gonnord P. & Costa M. & Peres M. & Ysebaert L. & Gadat S. & Valitutti S. Patient clustering  reveals CD8⁺ T cell central/effector memory dichotomy as an early marker of disease progression in chronic lymphocytic leukemia (2019) OncoImmunology, to appear.
• Costa M. & Gadat S. & Gonnord P. and Risser L.  Cytometry inference through adaptive atomic deconvolution (2019). Journal of Nonparametric Statistics, Volume 3, Number 2.
  

2018

• Gadat S. & Panloup F. & Saadane, S.  Stochastic Heavy Ball. Electronic Journal of Statistics,(2018) Volume 12, Number 1, 461-529.
• Gadat S. & Panloup F. & Saadane, S. Regret bound for Narendra-Shapiro bandit algorithms Stochastics, (2018), Volume 41, Number 1, 1744-2508. Matlab Implementation.
• Gadat S. & Gavra I. & Risser L.  How to calculate the barycenter of a weighted graph (2018) Mathematics of Operation Research, Volume 43, Number 4.

2017

• Ysebaert L., Cadot S., Kanoun S., Ken S., Recher C., Malgouyres F., Gadat S., Dupre L. and  Quillet Mary A.. Computational Integration to Model Tumor Dynamics in CLL Patients Treated with the Btk Inhibitor Ibrutinib (CompuTreatCLL): First Results of an Integrative Systems Biology Approach. (2017) Blood 130:2990.

2016

• Gadat S. & Klein T. & Marteau C. Classification with the nearest neighbor rule in general finite dimensional spaces, (2016) Annals of Statistics, Volume 44, Number 3, 982-1009.

2015

• Bouttier, C & Babando, O & Gadat, S & Gerchinovitz, S. & Laporte, S. & Nicol, F. Adaptive simulated annealing with homogenization for aircraft trajectory optimization (2015). Operation Research Proceedings.
• Chopin, N & Gadat, S. & Guedj, B. & Guyader, A. & Vernet, E.  On some recent advances in high dimensional Bayesian statistics. (2015) Esaim Proceedings and Surveys, Vol. 51, http://dx.doi.org/10.1051/proc/201551016.
• Gadat S.& Miclo, L. & Panloup F. A stochastic model for speculative bubbles. (2015) Alea, Latin American journal of probability and mathematical statistics, 12 (1), 491–532.
• Vasconcelos, Z. & Müller, S. & Wong, Y. & Gadat, S. & Valitutti, S. & Dupré, L. Individual human cytotoxic T Lymphocytes exhibit intraclonal heterogeneity in cumulative killing, (2015) Cell reports, Volume 11, Issue 9, p1474–1485, 9.
• Christophe, C. & Rodrigues, M. & Müller,S & Dupre,L. & Cattiaux,P & Gadat, S* and Valitutti, S* A biased competition theory of cytotoxic T lymphocytes interaction with tumor nodules, Plos One, (2015) DOI:10.1371/journal.pone.0120053.

2014

• Champion, M.& Chastaing, G. & Gadat, S. & Prieur, C. L2-boosting on a generalized Hoeffding decomposition for dependent variables. Application to sensitivity analysis, Statistica Sinica, (2014), doi:10.5705/ss.2013.310.
• Champion, M.& Cierco-Ayrolles, C. & Gadat, S. Vignes, M. Sparse regression and support recovery and support recovery with L2-Boosting algorithm, Journal of Statistical Planning and Inference, (2014), 155(C) :18–40.
• Bontemps D. & Gadat S. Bayesian methods for the Shape Invariant Model, Electronic Journal of Statistics (2014), 8:1522-1568.
• Gadat S.& Panloup F.  Long time behaviour and stationary regime of memory gradient diffusions Annales de l’Institut Henri Poincaré (B) (2014), 50 :564–601.
• Dedieu, D.& Delpierre, C. & Gadat, S. & Lang, T. & Lepage, B. & Savy, N.  Mixed Hidden Markov Model for Heterogeneous longitudinal data with missingness and errors in the Outcome variable . Journal de la Société Française de Statistique, (2014) Vol. 155 (1), 73-98.

2013

• Gadat S.& Panloup F. & Pellegrini C. Large Deviation Principle for invariant distributions of Memory Gradient Diffusions. Electronic Journal of Probability (2013), Volume 81, 1-34.
• Bigot J. & Gadat S.& Klein T. & Marteau C. Intensity estimation of non-homogeneous Poisson processes from shifted trajectories. Electronic Journal of Statistics, (2013), Volume 7 , 881-931.
• Gadat S.&  Miclo, L. Spectral decompositions and L2-operator norms of toy hypocoercive semi-groups. Kinetic and Related Models, (2013), Volume 6, Number 2, 317–372.

2012

• Bigot J. & Christophe C. & Gadat S. Random action of compact Lie groups and minimax estimation of a mean pattern. IEEE, Transactions on Information Theory, (2012), Vol 58, Nr 6  p.3509-3520.
• Cohen, S. & Dejean, S. & Gadat S.& Adaptive sequential design for regression on multi-resolution bases. Statistics and Computing, (2012), Vol 22, Nr 2, p.753-772.

2010

• Bigot J. & Gadat S. & Marteau C. Sharp template estimation in a shifted curves model. Electronic Journal of Statistics, (2010), Vol 4 p.994-1021.
• Bigot J. & Gadat S. A Deconvolution Approach to estimation of a common shape in a shifted curves model. Annals of Statistics, (2010), Vol 38, Nr 4 p.2422-2464.
• Bigot J. & Gadat S. Smoothing under diffeomorphic constraints with homeomorphic splines. SIAM, Journal on Numerical Analysis, (2010), Vol 48, Nr 1  p.224-243.

2009

• Cabot, A. & Engler, H. & Gadat S. On the long time behavior of second order differential equations with asymptotic small dissipation. Transactions of the American Mathematical Society, (2009), Vol 361,  p. 5983-6017.
• Bigot J. & Gadat S.& Loubes J.M. Statistical M-estimation and Consistency in large deformable models for Image Warping. Journal of Mathematical Imaging and Vision, (2009), Vol. 34, Nr. 3 , p. 270-290.
• Cabot, A. & Engler, H. & Gadat S. Second order differential equations with asymptotically small dissipation and piecewise flat potentials. Electronic Journal of Differential Equations, (2009), Vol 17, p.33-38.
• Villa N. & & Dkaki T. & Gadat S. & Inglebert J.-M. & Truong Q.-D. Community retrieval and visualization in large graphs. (2009), SciWatch Journal .
• Lê Cao K.A. & Gadat S.& Bonnet, A. Multiclass classification and gene selection with a stochastic algorithm. Computational Statistics and Data Analysis, (2009), Vol 53, Nr 10, p.3601-3615.

2008

• Gadat S. Jump Diffusion over Feature Space for object recognition. SIAM, Journal on Control and Optimization, (2008), Vol 47, Nr 2,  p.904-935.

2007

• Lê Cao K.A. & Gadat S. & Gonçalves O. & Besse P. Selection of Biologically Relevant Genes with a Wrapper Stochastic Algorithm. Statistical Applications in Genetics and Molecular  Biology, (2007), Vol 6, Nr 29.
• Gadat S.& Younès L. A stochastic algorithm for feature selection in pattern recognition. Journal of Machine Learning Research, (2007), Vol 8, p.509–547.

Unpublished manuscripts

• Cattiaux P. & Christophe C. & Gadat S. A stochastic model for cytotoxic T. Lymphocyte interaction with tumor nodules (2016).

 Some Slides:

• Non asymptotic bound for stochastic averaging
• On second order dynamics related to optimization
• Regret bound for NS bandit algorithms
• Classification with the nearest neighbor rule in general finite dimensional spaces
• Habilitation à Diriger les Recherches
• Shape Invariant Model: A nonparametric Bayesian point of view
• A Boosting algorithm for sensitivity analysis: Hoeffding decomposition with dependent variables
• Deformable models and statistical consistency rates
• Optimisation with averaged gradient_method (deterministic and stochastic methods)
• Averaged gradient diffusion
• M estimation for deformable models
• Adaptive Sequential planning with model selection

Rapports Techniques

• J.M. Azaïs and S. Gadat. Automatisation de l’estimation par valeurs extremes pour la mesure d’integrite. Technical report, Institut de Mathematiques de Toulouse, 2011.
• J.M. Azaïs, S. Gadat, A. Lagnoux, and C. Mercadier. Algorithmes de splitting pour la mesure d’integrite. Technical report, Institut de Mathematiques de Toulouse, Institut Camille Jordan Lyon I, 2010.
• J.M. Azaïs, S. Gadat, and C. Mercadier. etude de la mesure d’integrite par la methode des valeurs extrêmes. Technical report, Institut de Mathematiques de Toulouse, Institut Camille Jordan Lyon I, 2009.

 

Some recent Conferences  / Seminars:

• Statistics Seminar Lille  (June 2015): Regret of Narendra Shapiro bandit algorithms
• Statistics Seminar Oxford (April 2015): Regret of Narendra Shapiro bandit algorithms
• Statistics Seminar TSE (April 2015): Regret of Narendra Shapiro bandit algorithms
•  February 2014: Seminar of the CPTP: Some insights on interdiscipilnary research between statisticians and biologists
• November 2013: Mad Seminar – K nearest neighbour classification in general finite dimensional space.

• S. Gadat and D. Bontemps. Shape invariant model, a bayesian point of view. In Workshop of Bayes Non Parametric, 2013, Paris, France, September 2013
• Statistic seminar, Orsay  Mai 2013: Shape invariant model, a bayesian point of view
• S. Gadat. Bayesian consitency for deformable models in image processing. In Proceedings of the 3th Annual Conference of Mathematiques pour l’Image, Orleans, France, June 2012.
• Statistics Seminar TSE (April 2012): Bayesian estimation in deformable inverse problems
• BIA Statistics seminar ( March 2011): Adaptive optimal design and model selection
• J.M. Azaïs, D. Debailleux, S. Gadat, and N. Suard. Assessment of an ionosphere storm occurrence risk. In roceedings of the 2011 Conference ENC GNSS , London, England, November 2011.
• J.M. Azaïs, S. Gadat, and N. Suard. Ionosphere severe storms and occurrence risk estimation. In Proceedings of the 7th Conference Extreme Value Analysis, Probabilistic and Statistical Models and their Applications, Lyon, France, June 2011
• Montpellier Statistics Seminar (October 2010): Bayesian estimation in deformable inverse problems
• J.M. Azaïs, S. Gadat, C. Mercadier, and N. Suard. Gnss integrity achievement by using extreme value theory. In Proceedings of the 2009 Conference ION GNSS , San diego, USA, July 2009.
• N. Villa, T. Dkaki, S. Gadat, J.M. Inglebert, and Q.D. Truong. Recherche et representation de communautes dans des grands graphes. In Proceedings of VSST 2009, Nancy, France, 2009.
• S. Gadat. Markov hybrid process for variable selection in classication. In Proceedings of the 47th Conference on Decision and Control, Cancun, Mexico, December 2008.
• K.A. Lê Cao, S. Gadat, P. Besse, and O. Goncalves. Application of a stochastic algorithm for gene selection. In 5th Workshop of Statistical methods for post-genomic data, 2007 , Paris, France, 2007.
• S. Gadat, O. Gonalves, and K.A. Lê Cao. Gene selection with a stochastic algorithm for multiclass classification. In Proceedings of the 20th Annual Conference Proceedings of the 47th Conference Statistics for Data Mining, Learning and Knowledge Extraction, Aveiro, Portugal, August 2007.
• S. Gadat. Extraction of attributes for visual object recognition and dna microarray analysis. In IEEE Workshop on Statistical Signal Processing, Bordeaux,. 2005 , Bordeaux, France, July 2005.
• S. Gadat. Selection de variables pour la reconnaissance de formes. In GRETSI’05 On Image and Signal treatment, 2005, Louvain-La-Neuve, Belgique, September 2005.
• S. Gadat. Reflected jump-diffusion for genes selection and classication of micro-array data. In Workshop on Statistical Analysis of Postgenomic Data, 2005 , Paris, France, April 2005

• J. Bigot and S. Gadat. Chapter : Pattern recognition through large deformations of images, in book Pattern Recognition. Intech, 2010.
• S. Gadat. Chapter : Feature Selection in high dimension for face Detection, in book Advances in Face Image Analysis . Techniques and Technologies, IGI – Global, 2009.