Publications

* Authors listed in the alphabetical order, as is customary in some areas of mathematics, see the link. 

# These authors contributed equally.

Preprints

17. Radial Tail Repair: Post-training correction for diffusion and flow models, H. Cherkaoui#, H. Halconruy#, A. Ocello, 2026. Submitted.
       ArXiv version 

16. Tessellation localized transfer learning for nonparametric regression, H. Halconruy, B. Bobbia, P. Lejamtel.
        Preprint, 2026. In revision.
        ArXiv version

15. Multifractal analysis of random wavelet series with generalized Gaussian mixture statistics,
W. Ben Nasr*, H. Halconruy*, S. Jaffard*.
        Preprint, 2026.
Preprint 

14. Learning upper–lower value envelopes to shape online RL: A principled approach, S. Reboul, H. Halconruy.
        Preprint, 2025. Submitted.
        ArXiv version

13. Adaptive sample sharing for linear regression, H. Cherkaoui, H. Halconruy, Y. Petetin.
        Preprint, 2025. Submitted.
        ArXiv version

Publications

12. Do heavy tails help diffusion? On the subtle trade-off between initialization and training, H. Cherkaoui#, H. Halconruy#, A. Ocello.
40th Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.
        ArXiv version

11. Langevin-Informed Transfer Learning: Replacing the Target Samples by Black-Box Feedback, V. Kostic, K. Lounici, H. Halconruy, T. Devergne, M. Parrinello and M. Pontil.
        40th Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.
      ArXiv version 

10. Questioning Normality: A study of wavelet leaders distribution, W. Ben Nasr*, H. Halconruy*, S. Jaffard*.
        Statistics and Computing, 36, 1, 28, 2026.
        ArXiv version  

9. Laplace transform based low-complexity learning of continuous Markov semigroups, V. Kostic, K. Lounici, H. Halconruy, T. Devergne, P. Novelli and M. Pontil.
  18th International Conference on Machine Learning (ICML 2025), 2025.
    ArXiv version

8. Evolving privacy: drift parameter estimation for discretely observed i.i.d. diffusion processes under LDP, C. Amorino*, A. Gloter*, H. Halconruy*.
    Stochastic Processes and their Applications, 181, 104557, 2025.
    ArXiv version

7. Robust  density estimation  with the L1-loss. Applications to the estimation of a density on the line satisfying a shape constraint, with Y. Baraud*, H. Halconruy*, G. Maillard*.
    Les Annales de l'Institut Henri Poincaré, 61, 3, 2098-2148, 2025.
    ArXiv version

6. Learning the infinitesimal generator of stochastic diffusion processes, V. Kostic, H. Halconruy, K. Lounici, T. Devergne, M. Pontil.
     39th Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
    ArXiv version

5. On a projection least squares estimator for jump diffusion processes, H. Halconruy*, Nicolas Marie*.
      Annals of the Institute of Statistical Mathematics, 1-26, 2024.
      ArXiv version  

4. The insider problem in the trinomial model: a discrete jump process point of view, H. Halconruy.
    Decisions in Economics and Finance, 1-15, 2023.
    ArXiv version

3. Malliavin calculus for marked binomial processes and applications,  H. Halconruy.
    Electronic Journal of Probability, 27, 1-39, 2022.
      Paper link

2. Kernel Selection in Nonparametric Regression, H. Halconruy*, N. Marie*.
    Mathematical Methods of Statistics, 29, 1, 32-56, 2020.
    ArXiv version

1. Malliavin and Dirichlet structures for independent random variables,
    L. Decreusefond*, H. Halconruy*.
    Stochastic Processes and their Applications, 129, 8, 2611-2653, 2019.
    ArXiv version