Published in 27th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 238:2026–2034, 2024
A discriminator-free, sample-based alternative to adversarial GAN training for implicit generative models, based on the Invariant Statistical Loss (ISL).
Paper · Project page · Code · BibTeX
Published in International Conference on Machine Learning (ICML) 2026, 2026
Rank-statistic approximations of f-divergences that can be estimated directly from samples, with applications to sample-based comparison of real and generated distributions and relevance to f-GAN-style objectives.
Paper · Project page · Code · BibTeX
Published in 29th International Conference on Artificial Intelligence and Statistics (AISTATS) — Spotlight, 2026
Dual-ISL provides a convex, likelihood-free and discriminator-free objective for neural implicit samplers, offering a stable alternative to adversarial GAN-style training.
Paper · Project page · Code · BibTeX
Published in Journal of Machine Learning Research, 27(122):1–49, 2026
A stable, discriminator-free alternative to adversarial GAN training for implicit generative models, extended to multivariate and heavy-tailed distributions with Pareto-ISL and ISL-slicing.
Paper · Project page · Code · BibTeX
Published:
Lightning talk at CERN openlab on parallel task execution and an MCollective replacement.
Published:
Published:
Invited participant in a public discussion on science and Francophonie, drawing on the experience of the Semaine des jeunes talents scientifiques francophones.
Published:
Talk at JuliaHEP 2024 on training implicit generative models via an invariant statistical loss.
Published:
Published:
Research talk at the 2025 EMS School on training implicit generative models with an invariant statistical loss.
Published:
Research seminar on rank-based statistical learning and implicit generative modeling, with emphasis on sample-based objectives, distribution comparison, and robust training.
Published:
Research presentation in the Mathematics and Machine Learning special session on rank-based statistical learning, distribution comparison, and implicit generative modeling.
Published:
Seminar on Approximating f-Divergences with Rank Statistics, presenting a rank-based approach to f-divergence estimation without explicit density-ratio estimation.
Published:
Spotlight oral presentation at AISTATS 2026 on dual-ISL, a convex rank-based objective for implicit generative models that also yields an explicit density approximation.
Published:
Research seminar at the SiDOR group on sample-based distribution comparison, rank statistics, and applications to generative modeling.
Published:
Conference presentation at SEIO 2026 on rank-based methods for comparing distributions from samples and applications to generative modeling.
Published:
Invited seminar at the AUDIAS group (EPS-UAM) on sample-based distribution comparison, rank statistics, and implicit generative modeling.
Undergraduate course, University Carlos III of Madrid, Spain, 2023
Undergraduate course, University Carlos III of Madrid, Spain, 2024
Corporate training, Banco Bilbao Vizcaya Argentaria (BBVA), 2025
Course Instructor for BBVA internal Machine Learning training programs.
Student supervision, University Carlos III of Madrid, Spain, 2026