2 papers
cs.LG2026
VINA: Variational Invertible Neural Architectures
Shubhanshu Shekhar, Mohammad Javad Khojasteh, Ananya Acharya +2
The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural net…
math.OC2025
Data-Driven Discovery of PDEs via the Adjoint Method
Mohsen Sadr, Tony Tohme, Kamal Youcef-Toumi
In this work, we present an adjoint-based method for discovering the underlying governing partial differential equations (PDEs) given data. The idea is to consider a parameterized…