Yohann De Castro — Professor at Institut Camille Jordan

Latest News

[Jul 2026] Paper Node Regression on Latent Position Random Graphs via Local Averaging with M. Gjorgjevski, N. Keriven and S. Barthelmé published in the Journal of Machine Learning Research (JMLR), 27(88), 1-49, 2026. arXiv JMLR
[Jun 2026] New book Geometry of level sets of random fields: Kac-Rice formulas, Hermite expansions and applications with D. Armentano, J.-M. Azaïs, F. Dalmao, C. Delmas, J. R. León and E. Mordecki, published by Springer. PDF Springer
[Jun 2026] New paper Non-asymptotic Tail Bounds for the Kostlan–Shub–Smale Field: Tensor PCA and Spherical k-Spin Complexity with J.-M. Azaïs and F. Dalmao. Code arXiv
[Jun 2026] New version of Effective regions and kernels in continuous sparse regularization with R. Gribonval and N. Jouvin, accepted for publication in Information & Inference: A Journal of the IMA. arXiv
[May 2026] New version of Time series forecasting from partial observations via Non-negative Matrix Factorization with L. Mencarelli. arXiv
[May 2026] New paper Fast Spawn&Prune (FS&P): Global convergence of stochastic conic particle gradient descent via birth/death process with S. Gadat and C. Marteau, under review. Code arXiv
[May 2026] New version of Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems with P.-C. Aubin-Frankowski, A. Parmentier and A. Rudi, under review. arXiv
[Dec 2025] New paper Gaussian random field's anisotropy using excursion sets with J.-M. Azaïs and F. Dalmao, under review. Code
[Dec 2025] New version of Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test with J.-M. Azaïs and F. Dalmao, under review.

Quick Overview

Activities

Head of Site: Elected head of the École Centrale Lyon site of the Camille Jordan Institute.
Board Member: Statutory member of the ICJ laboratory council and the ECL management committee.
Associate Researcher: CERMICS, École Ponts ParisTech.
External Collaborator: OCKHAM Team, INRIA Lyon.

Teaching Duties

Course on Machine Learning (2A @ECL).
Course on Convexity and Parsimony (3A @ECL joint with Masters 2 MeA and Maths Avancées, Lyon 1/ENSL).

Books

Geometry of level sets of random fields: Kac-Rice formulas, Hermite expansions and applications.
D. Armentano, J.-M. Azaïs, F. Dalmao, Y. De Castro, C. Delmas, J. R. León, E. Mordecki.
Springer, 2026.
PDF Springer DOI

Research

My complete list of publications is available on HAL (Open Archives).

Non-asymptotic Tail Bounds for the Kostlan–Shub–Smale Field: Tensor PCA and Spherical k-Spin Complexity.
J.-M. Azaïs, F. Dalmao, Y. De Castro.
arXiv Preprint, 2026.
Probability PDF Code arXiv
Fast Spawn&Prune (FS&P): Global convergence of stochastic conic particle gradient descent via birth/death process.
Y. De Castro, S. Gadat, C. Marteau.
Under review, 2026.
Optimization Probability PDF Code arXiv
Gaussian random field's anisotropy using excursion sets.
J.-M. Azaïs, Y. De Castro, F. Dalmao.
Under review, 2025.
Probability Geometry PDF Code arXiv
Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test.
J.-M. Azaïs, Y. De Castro, F. Dalmao.
Under review, 2025.
Probability Geometry PDF Code arXiv
Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization.
Y. De Castro, R. Giard, C. Marteau.
Under review, 2025.
Learning Optimization PDF arXiv Zenodo
Effective regions and kernels in continuous sparse regularization.
Y. De Castro, R. Gribonval, N. Jouvin.
Information & Inference: A Journal of the IMA, to appear.
Learning Optimization PDF arXiv
Node Regression on Latent Position Random Graphs via Local Averaging.
M. Gjorgjevski, N. Keriven, S. Barthelmé, Y. De Castro.
Journal of Machine Learning Research (JMLR), 27(88), 1-49, 2026.
Graphs Optimization PDF arXiv JMLR
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems.
P.-C. Aubin-Frankowski, Y. De Castro, A. Parmentier, A. Rudi.
Under review, 2025.
Learning Optimization PDF arXiv
FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimization on Measures.
Y. De Castro, S. Gadat, C. Marteau.
arXiv Preprint, 2023 (Revised 2025).
Optimization Probability PDF arXiv
Exact recovery of the support of piecewise constant images via total variation regularization.
Y. De Castro, V. Duval, R. Petit.
Inverse Problems, 40(10), 2024.
Inverse Problems PDF Code arXiv IOP
SIGLE: valid Selective Inference procedure for Generalized Linear Lasso.
Y. De Castro, Q. Duchemin.
Under review, 2022.
Learning Probability PDF Code arXiv
Neural Networks beyond explainability: Selective inference for sequence motifs.
Y. De Castro, A. Villié, P. Veber, L. Jacob.
Transactions on Machine Learning Research (TMLR), 2023.
Learning Probability PDF arXiv OpenReview
Random Geometric Graph: Some recent developments and perspectives.
Q. Duchemin, Y. De Castro.
High Dimensional Probability IX, pp 347–392, 2023.
Graphs Probability PDF arXiv Springer
Minimax Estimation of Partially-Observed Vector AutoRegressions.
G. Dalle, Y. De Castro.
Electronic Journal of Statistics, 2025.
Graphs Probability PDF Code arXiv Euclid
Markov Random Geometric Graph (MRGG): A Growth Model for Temporal Dynamic Networks.
Y. De Castro, Q. Duchemin.
Electronic Journal of Statistics, 16, 671-699, 2022.
Graphs Probability PDF Code arXiv Euclid
Towards off-the-grid algorithms for total variation regularized inverse problems.
Y. De Castro, R. Petit, V. Duval.
Journal of Mathematical Imaging and Vision (JMIV), 2022.
Inverse Problems PDF Code arXiv Springer
Multiple Testing and Variable Selection along Least Angle Regression's path.
Y. De Castro, J.-M. Azaïs.
Information & Inference: A Journal of the IMA, 2022.
Learning Probability PDF Code arXiv OUP
Three rates of convergence or separation via U-statistics in a dependent framework.
Y. De Castro, Q. Duchemin, C. Lacour.
Journal of Machine Learning Research (JMLR), 23(201), 1-59, 2022.
Probability Learning PDF JMLR
Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains.
Y. De Castro, Q. Duchemin, C. Lacour.
Bernoulli Journal, 2022.
Probability Learning PDF arXiv Euclid
SuperMix: Sparse Regularization for Mixtures.
Y. De Castro, S. Gadat, C. Marteau, C. Maugis-Rabusseau.
Annals of Statistics, 49(3), 1779-1809, 2021.
Learning Optimization PDF arXiv Euclid
Dual optimal design and the Christoffel-Darboux polynomial.
Y. De Castro, F. Gamboa, D. Henrion, J.-B. Lasserre.
Optimization Letters, 15, 3-8, 2021.
Design Optimization PDF Springer
Time series forecasting from partial observations via Non-negative Matrix Factorization.
Y. De Castro, L. Mencarelli.
arXiv Preprint, 2021 (Revised 2026).
Learning Probability PDF arXiv
Testing Gaussian Process with Applications to Super-Resolution.
Y. De Castro, J.-M. Azaïs, S. Mourareau.
ACHA, 48, 445-481, 2020.
Learning Probability PDF Code arXiv Elsevier
Latent distance estimation for random geometric graphs.
Y. De Castro, E. Araya.
NeurIPS, 2019.
Geometry Probability PDF arXiv PMLR
On Representer Theorems and Convex Regularization.
Y. De Castro, C. Boyer, A. Chambolle, V. Duval, F. de Gournay, P. Weiss.
SIAM Journal on Optimization, 29(2), 2019.
Optimization Learning PDF arXiv SIAM
Approximate Optimal Designs for Multivariate Polynomial Regression.
Y. De Castro, F. Gamboa, D. Henrion, R. Hess, J.-B. Lasserre.
Annals of Statistics, 47(1), 127–155, 2019.
Algebra Optimization PDF Code arXiv Euclid
Nonnegative Matrix Factorization with Side Information for Time Series Recovery.
Y. De Castro, J.-M. Azaïs, Y. Goude, G. Hébrail, J. Mei.
IEEE Trans. Knowledge and Data Engineering, 31(3), 2019.
Learning Probability PDF arXiv IEEE
Sparse Recovery from Extreme Eigenvalues Deviation Inequalities.
Y. De Castro, S. Dallaporta.
ESAIM P&S, 23, 430-463, 2019.
Probability Learning PDF arXiv ESAIM
A short introduction to Moment-SoS hierarchies.
Y. De Castro.
Deuxième Congrès National de la SMF, 2018.
Algebra Optimization PDF
Adaptive Estimation of Nonparametric Geometric Graphs.
Y. De Castro, C. Lacour, T. M. Pham Ngoc.
Mathematical Statistics and Learning, 2(3/4), 2019.
Graphs Probability PDF arXiv EMS
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates.
J. Mei, Y. De Castro, Y. Goude, G. Hébrail.
ICML, 2017.
Optimization Learning PDF arXiv PMLR
Power of the Spacing test for Least-Angle Regression.
Y. De Castro, J.-M. Azaïs, S. Mourareau.
Bernoulli Journal, 24(1), 2018.
Probability Learning PDF arXiv Euclid
Exact solutions to Super Resolution on semi-algebraic domains in higher dimensions.
Y. De Castro, F. Gamboa, D. Henrion, J.-B. Lasserre.
IEEE Trans. Info. Theory, 63(1), 2017.
Algebra Optimization PDF Code arXiv IEEE
Adapting to Unknown Noise Level in Sparse Deconvolution.
Y. De Castro, C. Boyer, J. Salmon.
Information & Inference: A Journal of the IMA, 6(3), 2017.
Optimization Learning PDF arXiv OUP
Reconstructing undirected graphs from eigenspaces.
Y. De Castro, T. Espinasse, P. Rochet.
Journal of Machine Learning Research (JMLR), 18(51), 2017.
Graphs Algebra PDF arXiv JMLR
A Rice method proof of the Null-Space Property over the Grassmannian.
Y. De Castro, J.-M. Azaïs, S. Mourareau.
Annales de l'Institut Henri Poincaré, 53(4), 2017.
Probability Geometry PDF arXiv Euclid
Minimax adaptive estimation of non-parametric Hidden Markov Models.
Y. De Castro, É. Gassiat, C. Lacour.
Journal of Machine Learning Research (JMLR), 17(111), 2016.
Probability Learning PDF Code arXiv JMLR
Non-uniform spline recovery from small degree polynomial approximation.
Y. De Castro, G. Mijoule.
Journal of Mathematical Analysis and Applications (JMAA), Pages 971-992, 2015.
Optimization Learning PDF arXiv Elsevier
Spike Detection from Inaccurate Samplings.
Y. De Castro, J.-M. Azaïs, F. Gamboa.
ACHA, 38(2), 2015.
Optimization Learning PDF arXiv Elsevier
Randomized pick-freeze for sparse Sobol indices estimation in high dimension.
Y. De Castro, A. Janon.
ESAIM P&S, 19, 2015.
Probability Learning PDF arXiv ESAIM
Optimal designs for Lasso and Dantzig selector using Expander Codes.
Y. De Castro.
IEEE Trans. Info. Theory, 60(11), 2014.
Design Optimization PDF arXiv IEEE
Exact Reconstruction using Beurling Minimal Extrapolation.
Y. De Castro, F. Gamboa.
Journal of Mathematical Analysis and Applications (JMAA), 395(1), 2012.
Learning Optimization PDF arXiv Elsevier

Supervision

Ph.D. Students

Bruna ARAUJO (ShapeMed, Oct 2025–present) with Kaniav Kamary and Vivian Viallon;
Variational methods for causal inference in epidemiology.
Romane GIARD (ECL, Oct 2024–present) with Clément Marteau;
Towards optimal statistical bounds and algorithms for Unsupervised Learning.
Martin GJORGJEVSKI (ANR GrandMa, 2022-2025) with Simon Barthelmé and Nicolas Keriven;
On Statistical Learning Theory for Random Graphs. PhD defended 2025.
Guillaume DALLE (IPEF, 2019-2022) with Axel Parmentier;
OR and ML. Now Researcher at Ponts ParisTech.
Quentin DUCHEMIN (DIM Math Innov, 2019-2022) with Claire Lacour;
Random Graphs and Post-Selection Inference. Now Researcher at SDSC (EPFL).
Romain PETIT (DIM Math Innov, 2019-2022) with Vincent Duval;
Off-the-grid methods. Now Assistant Professor at LPSM, Sorbonne Université.
Antoine VILLIÉ (LBBE, 2019-2022) with Laurent Jacob;
Kernel Post-Selection Inference. Senior Researcher at Aurobac Therapeutics.
Ernesto ARAYA (Orsay grant, 2017-2020);
Random Graphs. Post-Doc in Machine Learning.
Jiali MEI (ÉDF CIFRE, 2014-2017) with Jean-Marc Azaïs, Yannig Goude and Georges Hébrail;
“Time series recovery and prediction with regression-enhanced nonnegative matrix factorization applied to electricity consumption”.
Prix Paul Caseau de l'Académie des Sciences, 2018. Senior Researcher at BNP Paribas.

Post-Docs

Gaël POUX (2025-2026), Bio-Statistics at IARC, WHO.
Nicolas JOUVIN (2021), Sparse regularization on measures. Now Chargé de Recherche @INRAE.
Luca MENCARELLI (2018-2020), Matrix factorization for Time Series. Now Assistant Professor at Pisa University.
Guillaume MIJOULE (2018-2019), Semi-discrete Optimal Transport. Now Data Scientist in Paris Greater Area.

Teaching

Machine Learning (2nd year -- Master 1)
More detail at machine-learning-centrale.github.io.
Convexity and Parsimony (3rd year -- Master 2)
More detail at statistical-learning-centrale.github.io.

Vitae

Spring 2023	Full Professor (Promoted by CNU)
2022 - 2027	Junior Member, Institut Universitaire de France (IUF)
Since 2019	Professor, Institut Camille Jordan, École Centrale Lyon
2018-2019	Senior Researcher, CERMICS, École Ponts ParisTech
2017-2018	Invited Researcher, Inria Paris (MOKAPLAN Team)
Nov 2016	Habilitation (H.D.R)
2012-2016	Associate Professor, Institut de Mathématique d'Orsay
Dec 2011	Ph.D. Thesis
2008-2012	Ph.D. Student, Institut de Mathématiques de Toulouse
2004-2009	Student, École Normale Supérieure

Contact

Institut Camille Jordan
École Centrale de Lyon
36 Avenue Guy de Collongue
69134 Écully, France
Locate on Map