A covariance-ratio-based gradient-free method identifies likelihood-informed subspaces for dimension reduction in Bayesian inference, yielding better posterior approximations in linear Gaussian settings and practical results in nonlinear high-dimensional applications.
Covariance-based MCMC for high-dimensional Bayesian updating with Sequential Monte Carlo.Probabilistic Engineering Mechanics, 77:103667, July 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Covariance-Informed Subspace: an Adaptive Gradient-Free Input Dimension Reduction Method for Bayesian Inference
A covariance-ratio-based gradient-free method identifies likelihood-informed subspaces for dimension reduction in Bayesian inference, yielding better posterior approximations in linear Gaussian settings and practical results in nonlinear high-dimensional applications.