Research
-
G. Lecué and Z. Shang
A geometrical viewpoint on the benign overfitting property of the minimum l2-norm interpolant estimator.
Submitted, 2022. -
J. Depersin and G. Lecué
Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
To appear in Probability theory and related fields -
J. Depersin and G. Lecué
On the robustness to adversarial corruption and to heavy-tailed data of the Stahel-Donoho median of means
Submitted, 2021. -
S. Chrétien, M. Cucuringu, G. Lecué and L. Neirac
Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature
Journal of Machine Learning Research, 1 - 64, 2021. -
J. Depersin and G. Lecué
Robust subgaussian estimator of a mean vector in nearly linear time
The Annals of Statistics, volume 50, Number 1, (2022), 511-536. bibtex -
G. Chinot, G. Lecué and M. Lerasle
Robust high dimensional learning for Lipschitz and convex losses
Journal of machine Learning research (233):1−47, 2020. -
J. Kwon, G. Lecué and M. Lerasle
Median of means principle as a divide-and-conquer procedure for robustness, sub-sampling and hyper-parameters tuning
Electronic journal of statistics, 15, 1, (2021), 1202-1227
Python notebook and codes available here -
G. Chinot, G. Lecué and M. Lerasle
Statistical Learning with Lipschitz and convex loss functions
Probability theory and related fields, (233):1−47, 2020. . Python notebook available here -
M. Lerasle, T. Matthieu, Z. Szabo and G. Lecué
MONK – Outliers-Robust Mean Embedding Estimation by Median-of-Means
ICML 2019. See PMLR for supplementary files and code. -
G. Lecué, M. Lerasle and T. Matthieu
Robust classification via MOM minimization
Machine Learning research, 109, 8, (2020), 1635-166
Python notebooks available here -
R. Deswarte and G. Lecué
minimax regularization
Under revision in Journal of complexity -
Ph. Mesnard, C. Enderli and G. Lecué
Ground clutter processing for airborne radar in a Compressed Sensing context
CoSeRa 2018: Compressive Sensing Radar. -
Ph. Mesnard, C. Enderli and G. Lecué
Periodic Patterns Frequency Hopping Waveforms : from conventional Matched Filtering to a new Compressed Sensing Approach
IRS 2018: Internal Radar Symposium. -
G. Lecué and M. Lerasle
Robust Machine Learning by median of means: theory and practice
The Annals of Statistics, Volume 48, Number 2 (2020), 906-931..
Supplementary material available here
Python notebooks available here -
S. Foucart and G. Lecué
An IHT algorithm for sparse recovery from subexponential measurements
IEEE Signal Processing Letters (9) 24, 2017. -
P. Alquier, V. Cottet and G. Lecué
Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
The Annals of Statistics, 47(4):2117-2144, 2019
Supplementary material here
Python notebooks available here -
P. Bellec, G. Lecué and A. Tsybakov
Towards the study of least squares estimators with convex penalty
In Séminaire et Congrès, number 31. Société mathématique de France, 2017. -
G. Lecué and M. Lerasle
Learning from MOM’s principles: Le Cam’s approach
Stochastic processes and their applications, Volume 129, Issue 11, November 2019, Pages 4385-4410. -
P. Bellec, G. Lecué and A. Tsybakov
Slope meets Lasso: improved oracle bounds and optimality
The Annals of Statistics, 46(6B):3603–3642, 2018. -
G. Lecué and S. Mendelson
Regularization and the small-ball method II: complexity dependent error rates
Journal of Machine Learning Research, 18(146):1−48, 2017. -
G. Lecué and S. Mendelson
Regularization and the small-ball method I: sparse recovery
The Annals of Statistics, Volume 46, Number 2 (2018), 611-641. Supplementary material here -
S. Dirksen, G. Lecué and H. Rauhut.
On the gap between RIP-properties and sparse recovery conditions
IEEE Trans. Inform. Theory 64(8):5478 - 5487, 2018.
Notebooks available at here for exact reconstruction via Douglas Rachford and here for estimation results for quantized measurements. -
G. Lecué and S. Mendelson.
Performance of empirical risk minimization in linear aggregation
Bernoulli journal 22 (2016), no. 3, 1520–1534. -
G. Lecué and S. Mendelson.
Sparse recovery under weak moment assumptions
Journal of the European Mathematical society, Volume 19, Issue 3, 2017, pp. 881–904 -
G. Lecué and S. Mendelson.
Minimax rates of convergence and the performance of ERM in phase recovery
Electronic Journal of Probability, 20 (2015) no. 57, 29 pp. -
G. Lecué and S. Mendelson.
Learning Subgaussian classes : Upper and minimax bounds
To appear in Topics in Learning Theory - Societe Mathématique de France, (S. Boucheron and N. Vayatis Eds.) -
G. Lecué.
Comment to ‘Generic chaining and the l1-penalty’ by Sara van de Geer
Journal of statistical and planning inference, Volume 143, Issue 6, Pages 1022-1025 (June 2013). -
G. Lecué and P. Rigollet.
Optimal learning with Q-aggregation
The Annals of Statistics, 42 (2014), no. 1, 211-224. -
G. Lecué.
Empirical risk minimization is optimal for the convex aggregation problem
Bernoulli journal 19 (2013), no. 5B, 2153–2166. -
D. Chafaï, O. Guédon, G. Lecué and A. Pajor.
Interactions between compressed sensing, Random matrices and high-dimensional geometry
Collection Panoramas et synthèse of the Société mathématique de France. Volume 37 (2012), 182 pages. -
G. Lecué and S. Mendelson.
On the optimality of the empirical risk minimization procedure for the convex aggregation problem
Annales de l’institut Henri Poincaré Probabilité et Statistiques, 49 (1), p. 288-306, 2013. -
G. Lecué and S. Mendelson.
On the optimality of the aggregate with exponential weights for low temperatures
Bernoulli journal 19 (2013), no. 2, 646–675. -
G. Lecué and S. Mendelson.
General non-exact oracle inequalities in the unbounded case
The Annals of Statistics, 40 (2), p. 832-860. 2012. \ Supplementary material to “General non-exact oracle inequalities in the unbounded case -
G. Lecué and C. Mitchell.
Oracle inequalities for cross-validation type procedures
Electronic journal of statistics, (6), p. 1803-1837. 2012. -
S. Gaïffas and G. Lecué.
Sharp oracle inequalities for high-dimensional matrix prediction
IEEE Transactions on Information Theory, 57 (10), p. 6942-6957, 2011. -
S. Gaïffas and G. Lecué.
Hyper-sparse optimal aggregation
Journal of Machine Learning research, 12(Jun):1813-1833, 2011. -
G. Lecué and S. Mendelson.
Sharper lower bounds on the performance of the Empirical Risk Minimization Algorithm
Bernoulli journal, 16(3), 2010, p. 605-613, 2010. -
G. Lecué and S. Mendelson.
Aggregation via Empirical Risk Minimization
Probability theory and related fields, Vol. 145, Number 3-4, pp. 591-613. Novembre, 2009. -
C. Chesneau and G. Lecué.
Adapting to Unknown Smoothness by Aggregation of Thresholded Wavelet Estimators
Statistica Sinica, Vol. 19, Number 4, October 2009, pp. 1407-1418. -
K. Bertin and G. Lecué.
Selection of variables and dimension reduction in high-dimensional non-parametric regression
Electronic Journal of Statistics, Vol. 2, pp. 1224-1241. 2008. -
G. Lecué.
Classification with minimax fast rates for Classes of Bayes Rules with Sparse Representation
Electronic Journal of Statistics, Vol. 2, pp. 741-773. 2008. -
S. Gaïffas and G. Lecué.
Optimal rates and adaptation in the Single-Index Model using aggregation
Electronic Journal of Statistics, Vol. 1, pp. 538-573. 2007. -
G. Lecué.
Suboptimality of Penalized Empirical Risk Minimization In Classification
20th Annual Conference On Learning Theory, COLT07. Proceedings. Bshouty, Gentile (Eds.). Springer. LNAI 4539, 142-156. Springer. -
G. Lecué.
Optimal rates of aggregation in classification under low noise assumption
Bernoulli Journal 13(4), p. 1000-1022, 2007. -
G. Lecué.
Simultaneous adaptation to the margin and to complexity in classification
The Annals of Statistics, Vol. 35, No. 4. p. 1698-1721. August 2007. -
G. Lecué.
Optimal oracle inequality for aggregation of classifiers under low noise condition
19th Annual Conference On Learning Theory, COLT06. Proceedings. Gabor Lugosi, Hans Ulrich Simon (Eds.). Springer. LNAI 2006, p. 364-378. “Mark Fulk award” for the best student paper. -
G. Lecué.
Lower Bounds and Aggregation in Density Estimation
Journal of Machine Learning Research, 7(Jun):971-981, 2006.