Fabricio Arend Torres — accepted AI-conference papers

2024

Lagrangian Flow Networks for Conservation Laws

Fabricio Arend Torres, Marcello Massimo Negri, Marco Inversi, Jonathan Aellen, Volker Roth

ICLR 2024spotlight

We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. By construction, the proposed LFlows satisfy the continuity equation, a PDE describing mass conservation in its differential form. Our model is based on the insight that soluti…

Cited by 3 Source ↗PDF ↗Scholar ↗

2023

Conditional Matrix Flows for Gaussian Graphical Models

Marcello Massimo Negri, Fabricio Arend Torres, Volker Roth

NeurIPS 2023poster

Studying conditional independence among many variables with few observations is a challenging task. Gaussian Graphical Models (GGMs) tackle this problem by encouraging sparsity in the precision matrix through $l_q$ regularization with $q\leq1$. However, most GMMs rely on the $l_1$ norm because the o…

Cited by 3 Source ↗PDF ↗Scholar ↗