BayesFlow: Learning complex stochastic models with invertible neural networks
Estimating the parameters of mathematical models is a common problem in almost all
branches of science. However, this problem can prove notably difficult when processes and …
branches of science. However, this problem can prove notably difficult when processes and …
Coupling-based invertible neural networks are universal diffeomorphism approximators
Invertible neural networks based on coupling flows (CF-INNs) have various machine
learning applications such as image synthesis and representation learning. However, their …
learning applications such as image synthesis and representation learning. However, their …
Derivative-informed neural operator: an efficient framework for high-dimensional parametric derivative learning
We propose derivative-informed neural operators (DINOs), a general family of neural
networks to approximate operators as infinite-dimensional map**s from input function …
networks to approximate operators as infinite-dimensional map**s from input function …
Coupling techniques for nonlinear ensemble filtering
We consider filtering in high-dimensional non-Gaussian state-space models with intractable
transition kernels, nonlinear and possibly chaotic dynamics, and sparse observations in …
transition kernels, nonlinear and possibly chaotic dynamics, and sparse observations in …
Sampling in unit time with kernel fisher-rao flow
We introduce a new mean-field ODE and corresponding interacting particle systems (IPS)
for sampling from an unnormalized target density. The IPS are gradient-free, available in …
for sampling from an unnormalized target density. The IPS are gradient-free, available in …
Certified dimension reduction in nonlinear Bayesian inverse problems
We propose a dimension reduction technique for Bayesian inverse problems with nonlinear
forward operators, non-Gaussian priors, and non-Gaussian observation noise. The …
forward operators, non-Gaussian priors, and non-Gaussian observation noise. The …
On the representation and learning of monotone triangular transport maps
Transportation of measure provides a versatile approach for modeling complex probability
distributions, with applications in density estimation, Bayesian inference, generative …
distributions, with applications in density estimation, Bayesian inference, generative …
Conditional sampling with monotone GANs: From generative models to likelihood-free inference
We present a novel framework for conditional sampling of probability measures, using block
triangular transport maps. We develop the theoretical foundations of block triangular …
triangular transport maps. We develop the theoretical foundations of block triangular …
A dimension-reduced variational approach for solving physics-based inverse problems using generative adversarial network priors and normalizing flows
We propose a novel modular inference approach combining two different generative models—
generative adversarial networks (GAN) and normalizing flows—to approximate the posterior …
generative adversarial networks (GAN) and normalizing flows—to approximate the posterior …
[HTML][HTML] Efficiency comparison of MCMC and Transport Map Bayesian posterior estimation for structural health monitoring
In this paper, an alternative to solving Bayesian inverse problems for structural health
monitoring based on a variational formulation with so-called transport maps is examined …
monitoring based on a variational formulation with so-called transport maps is examined …