Author

Beatriz Seoane

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2025

PRIVET: PRoximIty leakage detection Via Extreme value Theory

It is empirically demonstrated that PRIVET detects memorization and more subtle forms of proximity-based data leakage across diverse data modalities, including settings with very high dimensionality and limited sample sizes such as genetic data, and in underfitting regimes that overfitting-based diagnostics cannot reac...

Antoine Szatkownik, A. Decelle, Beatriz Seoane et al. · 1 citation

#machine learning Preprint Jul 2026

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to mai...

Nicolas B'ereux, A. Decelle, Cyril Furtlehner et al. · 0 citations