pub type TransformedNutsSettings = NutsSettings<TransformedSettings>;Aliased Type§
pub struct TransformedNutsSettings {
pub num_tune: u64,
pub num_draws: u64,
pub maxdepth: u64,
pub mindepth: u64,
pub store_gradient: bool,
pub store_unconstrained: bool,
pub max_energy_error: f64,
pub store_divergences: bool,
pub adapt_options: TransformedSettings,
pub check_turning: bool,
pub num_chains: usize,
pub seed: u64,
}Fields§
§num_tune: u64The number of tuning steps, where we fit the step size and mass matrix.
num_draws: u64The number of draws after tuning
maxdepth: u64The maximum tree depth during sampling. The number of leapfrog steps is smaller than 2 ^ maxdepth.
mindepth: u64The minimum tree depth during sampling. The number of leapfrog steps is larger than 2 ^ mindepth.
store_gradient: boolStore the gradient in the SampleStats
store_unconstrained: boolStore each unconstrained parameter vector in the sampler stats
max_energy_error: f64If the energy error is larger than this threshold we treat the leapfrog step as a divergence.
store_divergences: boolStore detailed information about each divergence in the sampler stats
adapt_options: TransformedSettingsSettings for mass matrix adaptation.
check_turning: bool§num_chains: usize§seed: u64