Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Negri, Marcello Massimo"'
Normalizing Flows (NFs) are powerful and efficient models for density estimation. When modeling densities on manifolds, NFs can be generalized to injective flows but the Jacobian determinant becomes computationally prohibitive. Current approaches eit
Externí odkaz:
http://arxiv.org/abs/2406.09116
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 $q\leq1$. Howev
Externí odkaz:
http://arxiv.org/abs/2306.07255
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 differentiable
Externí odkaz:
http://arxiv.org/abs/2305.16846
Autor:
Torres, Fabricio Arend, Negri, Marcello Massimo, Nagy-Huber, Monika, Samarin, Maxim, Roth, Volker
Physics-informed Neural Networks (PINNs) have recently emerged as a principled way to include prior physical knowledge in form of partial differential equations (PDEs) into neural networks. Although PINNs are generally viewed as mesh-free, current ap
Externí odkaz:
http://arxiv.org/abs/2206.01545