Derives that the MC replica method produces a distribution differing from the Bayesian Laplace approximation by a single computable matrix (residual-weighted Hessian), whose sign and magnitude determine over- or under-estimation of uncertainties in nonlinear models.
A critical study of the Monte Carlo replica method
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
hep-ph 3verdicts
UNVERDICTED 3representative citing papers
Presents a linear PDF parametrization from dimensionality-reduced neural network bases for efficient Bayesian inference, tested via multi-closure tests on synthetic deep inelastic scattering data.
Presents a new ensemble regression hyperoptimisation procedure for PDF fitting that combines multiple statistically equivalent methodologies into one PDF set accounting for hyperparameter variation.
citing papers explorer
-
Propagating data noise through the fit: the Monte Carlo replica distribution
Derives that the MC replica method produces a distribution differing from the Bayesian Laplace approximation by a single computable matrix (residual-weighted Hessian), whose sign and magnitude determine over- or under-estimation of uncertainties in nonlinear models.
-
A linear PDF model for Bayesian inference
Presents a linear PDF parametrization from dimensionality-reduced neural network bases for efficient Bayesian inference, tested via multi-closure tests on synthetic deep inelastic scattering data.
-
Hyperoptimisation algorithm for the next generation of PDF determinations: ensemble regression with an unbiased selection model
Presents a new ensemble regression hyperoptimisation procedure for PDF fitting that combines multiple statistically equivalent methodologies into one PDF set accounting for hyperparameter variation.