no code implementations • 1 Dec 2023 • John D. Lee, Jakob Richter, Martin R. Pfaller, Jason M. Szafron, Karthik Menon, Andrea Zanoni, Michael R. Ma, Jeffrey A. Feinstein, Jacqueline Kreutzer, Alison L. Marsden, Daniele E. Schiavazzi
The substantial computational cost of high-fidelity models in numerical hemodynamics has, so far, relegated their use mainly to offline treatment planning.
1 code implementation • 24 Jul 2023 • Guoxiang Grayson Tong, Carlos A. Sing Long, Daniele E. Schiavazzi
Use of generative models and deep learning for physics-based systems is currently dominated by the task of emulation.
1 code implementation • 10 Jul 2023 • Yu Wang, Emma R. Cobian, Jubilee Lee, Fang Liu, Jonathan D. Hauenstein, Daniele E. Schiavazzi
Variational inference is an increasingly popular method in statistics and machine learning for approximating probability distributions.
1 code implementation • 11 Feb 2023 • Bingyue Su, Yu Wang, Daniele E. Schiavazzi, Fang Liu
We use normalizing flows (NF), a family of deep generative models, to estimate the probability density of a dataset with differential privacy (DP) guarantees, from which privacy-preserving synthetic data are generated.
1 code implementation • 5 Jul 2022 • Guoxiang Grayson Tong, Daniele E. Schiavazzi
We propose a data-driven framework to increase the computational efficiency of the explicit finite element method in the structural analysis of soft tissue.
no code implementations • 10 May 2022 • Lauren Partin, Gianluca Geraci, Ahmad Rushdi, Michael S. Eldred, Daniele E. Schiavazzi
We analyze the regression accuracy of convolutional neural networks assembled from encoders, decoders and skip connections and trained with multifidelity data.
1 code implementation • 1 Feb 2022 • Emma R. Cobian, Jonathan D. Hauenstein, Fang Liu, Daniele E. Schiavazzi
We demonstrate the computational efficiency of the AdaAnn scheduler for variational inference with normalizing flows on a number of examples, including density approximation and parameter estimation for dynamical systems.
1 code implementation • 11 Jan 2022 • Lauren Partin, Daniele E. Schiavazzi, Carlos A. Sing Long
Novel Magnetic Resonance (MR) imaging modalities can quantify hemodynamics but require long acquisition times, precluding its widespread use for early diagnosis of cardiovascular disease.
1 code implementation • 28 Aug 2021 • Yu Wang, Fang Liu, Daniele E. Schiavazzi
To reduce the computational cost without sacrificing inferential accuracy, we propose Normalizing Flow with Adaptive Surrogate (NoFAS), an optimization strategy that alternatively updates the normalizing flow parameters and surrogate model parameters.
1 code implementation • 22 Jan 2021 • Xue Li, Daniele E. Schiavazzi
Computational models are increasingly used for diagnosis and treatment of cardiovascular disease.
Computational Engineering, Finance, and Science Numerical Analysis Numerical Analysis