no code implementations • 22 May 2024 • Qiuyi Chen, Panagiotis Tsilifis, Mark Fuge
Recently, generative models such as Generative Adversarial Networks (GANs) have shown great potential in approximating complex high dimensional conditional distributions and have paved the way for characterizing posterior densities in Bayesian inverse problems, yet the problems' high dimensionality and high nonlinearity often impedes the model's training.
no code implementations • 5 Aug 2020 • Panagiotis Tsilifis, Piyush Pandita, Sayan Ghosh, Valeria Andreoli, Thomas Vandeputte, Liping Wang
We present a Bayesian approach to identify optimal transformations that map model input points to low dimensional latent variables.
no code implementations • 23 Dec 2019 • Panagiotis Tsilifis, Iason Papaioannou, Daniel Straub, Fabio Nobile
The challenges for non-intrusive methods for Polynomial Chaos modeling lie in the computational efficiency and accuracy under a limited number of model simulations.
no code implementations • 6 Jan 2018 • Panagiotis Tsilifis, Xun Huan, Cosmin Safta, Khachik Sargsyan, Guilhem Lacaze, Joseph C. Oefelein, Habib N. Najm, Roger G. Ghanem
Basis adaptation in Homogeneous Chaos spaces rely on a suitable rotation of the underlying Gaussian germ.
no code implementations • 30 May 2015 • Panagiotis Tsilifis, Roger G. Ghanem, Paris Hajali
We propose a framework where a lower bound of the expected information gain is used as an alternative design criterion.
2 code implementations • 21 Oct 2014 • Panagiotis Tsilifis, Ilias Bilionis, Ioannis Katsounaros, Nicholas Zabaras
The classical approach to inverse problems is based on the optimization of a misfit function.