From c25ec9bd5f8a26e281060074a52c99a8111e475a Mon Sep 17 00:00:00 2001 From: "Documenter.jl" Date: Tue, 5 Sep 2023 15:33:08 +0000 Subject: [PATCH] build based on 02be1d2 --- dev/design/index.html | 2 +- dev/index.html | 2 +- dev/search/index.html | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/dev/design/index.html b/dev/design/index.html index 7d365e6..7a9176b 100644 --- a/dev/design/index.html +++ b/dev/design/index.html @@ -94,4 +94,4 @@ else set!(sampler, stepsize_adapter, ...) end -end

When a Stan sampler is passed into the adapt!(...) function above, the adapter within the variable trajectorylength_adapter has type TrajectorylengthConstant. The method update!(...) dispatches to the function appropriate to this type and results in a no-op.

+end

When a Stan sampler is passed into the adapt!(...) function above, the adapter within the variable trajectorylength_adapter has type TrajectorylengthConstant. The method update!(...) dispatches to the function appropriate to this type and results in a no-op.

diff --git a/dev/index.html b/dev/index.html index 69c5eaf..5e47c32 100644 --- a/dev/index.html +++ b/dev/index.html @@ -1,2 +1,2 @@ -Home · MCBayes.jl
Edit on GitHub

MCBayes.jl

MCBayes.jl is Julia package for Bayesian inference, which only depends on Julia standard library packages.

MCBayes.Stan — Type
Stan(dims, chains, T = Float64; kwargs...)

Initialize Stan sampler object. The number of dimensions dims and number of chains chains are the only required arguments. The type T of the ...

Optionally, via keyword arguments, can set the metric, stepsize, seed, maxtreedepth, and maxdeltaH.

source
Missing docstring.

Missing docstring for sample!. Check Documenter's build log for details.

MCBayes.StepsizeDualAverage — Type
StepsizeDualAverage(initial_stepsize::Vector)

Construct a stepsize adapter using the dual averaging method by Nesterov 2009, as used in Stan. The length of initial_stepsize::Vector must be appropriate for the sampling algorithm for which this stepsize adapter will be used.

source
MCBayes.StepsizeConstant — Type
StepsizeConstant(initial_stepsize::Vector)

Construct a stepsize adapter for which the stepsize is fixed at it's initial value.

source
MCBayes.OnlineMoments — Type
OnlineMoments(d, c, update = true)

Returns an OnlineMoments struct with mean and variance Matrixes of size (d, c). When update!(om::OnlineMoments, x::Matrix) is called, update determines whether or not any updates will actually be applied.

source
MCBayes.update! — Function

Adam update.

source
update!(om::OnlineMoments, x::AbstractMatrix; kwargs...)

Update om's mean and variance Matrixes with the data contained in x. The rows of x and om.m (and thus om.v) must match. The columns of x and om.m must either match or om.m must have only 1 column. In the latter case, all columns of x will be used to update the same moments om.m and om.v.

source

Assumes x is centered and scaled

source

Centers x::AbstractVector using location and scale

source

Centers x using location and scale

source

Adam update on log-scale.

source
+Home · MCBayes.jl
Edit on GitHub

MCBayes.jl

MCBayes.jl is Julia package for Bayesian inference, which only depends on Julia standard library packages.

MCBayes.Stan — Type
Stan(dims, chains, T = Float64; kwargs...)

Initialize Stan sampler object. The number of dimensions dims and number of chains chains are the only required arguments. The type T of the ...

Optionally, via keyword arguments, can set the metric, stepsize, seed, maxtreedepth, and maxdeltaH.

source
Missing docstring.

Missing docstring for sample!. Check Documenter's build log for details.

MCBayes.StepsizeDualAverage — Type
StepsizeDualAverage(initial_stepsize::Vector)

Construct a stepsize adapter using the dual averaging method by Nesterov 2009, as used in Stan. The length of initial_stepsize::Vector must be appropriate for the sampling algorithm for which this stepsize adapter will be used.

source
MCBayes.StepsizeConstant — Type
StepsizeConstant(initial_stepsize::Vector)

Construct a stepsize adapter for which the stepsize is fixed at it's initial value.

source
MCBayes.OnlineMoments — Type
OnlineMoments(d, c, update = true)

Returns an OnlineMoments struct with mean and variance Matrixes of size (d, c). When update!(om::OnlineMoments, x::Matrix) is called, update determines whether or not any updates will actually be applied.

source
MCBayes.update! — Function

Adam update.

source
update!(om::OnlineMoments, x::AbstractMatrix; kwargs...)

Update om's mean and variance Matrixes with the data contained in x. The rows of x and om.m (and thus om.v) must match. The columns of x and om.m must either match or om.m must have only 1 column. In the latter case, all columns of x will be used to update the same moments om.m and om.v.

source

Assumes x is centered and scaled

source

Centers x::AbstractVector using location and scale

source

Centers x using location and scale

source

Adam update on log-scale.

source
diff --git a/dev/search/index.html b/dev/search/index.html index a65b8ac..547607e 100644 --- a/dev/search/index.html +++ b/dev/search/index.html @@ -1,2 +1,2 @@ -Search · MCBayes.jl

Loading search...

    +Search · MCBayes.jl

    Loading search...