Giovanni Catania — accepted AI-conference papers

2025

A Theoretical Framework For Overfitting In Energy-based Modeling

Giovanni Catania, Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane

ICML 2025poster

We investigate the impact of limited data on training pairwise energy-based models for inverse problems aimed at identifying interaction networks. Utilizing the Gaussian model as testbed, we dissect training trajectories across the eigenbasis of the coupling matrix, exploiting the independent evolut…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Explaining the effects of non-convergent MCMC in the training of Energy-Based Models

Elisabeth Agoritsas, Giovanni Catania, Aurélien Decelle, Beatriz Seoane

ICML 2023poster

In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-Based models (EBMs). In particular, we show analytically that EBMs trained with non-persistent short runs to estimate the gradient can perfectly reproduce a set of empirical statistics of the data, not at the…

Cited by 4 Source ↗PDF ↗Scholar ↗