GPLikelihoods.jl
GPLikelihoods.jl copied to clipboard
JuliaGaussianProcesses
Provides likelihood functions for Gaussian Processes.
This PR generalizes all `expected_loglikelihood` methods to also accept `AbstractVector`s, such that it can be used for input-dependent (e.g. heteroskedastic) likelihoods. See e.g. https://github.com/JuliaGaussianProcesses/AbstractGPs.jl/pull/216
I cannot count how many times I lost nerves on debugging issues on my script to only find out that I used categorical variables instead of 0-1 for my `BernoulliLikelihood`....
With the `NBParamII` for sufficiently large values of `f` (something like 800), `p` will be equal to zero and many estimator starts to break down. This might be something to...
For convenience, the old version of `expected_loglikelihood` (Gauss-Hermite quadrature method) looked like this: https://github.com/JuliaGaussianProcesses/GPLikelihoods.jl/blob/e9b7da99e46f56859209ff27bbb36d12512d0ad4/src/expectations.jl#L83-L109 #90 introduced a work-around/hack for two (possibly interrelated) issues of that implementation: - Computing the gradient...
https://github.com/JuliaStats/Distributions.jl/pull/1536 is proposing different parametrizations of the NegativeBinomial likelihood, particularly the scale-shape parametrization that corresponds to the NBParamMean types introduced in #80. Once https://github.com/JuliaStats/Distributions.jl/pull/1536 is released as part of Distributions.jl,...
- [ ] Ordinal - [ ] Truncated Gaussian - [ ] Cauchy - [ ] InverseGamma - [ ] Laplace - [ ] Student-T #79 Please edit directly to...
Implement a likelihood with the [Student-T distribution](https://en.wikipedia.org/wiki/Student%27s_t-distribution). The input GP corresponds to the mean in the following definition of the [non-standardized Student-t distribution](https://en.wikipedia.org/wiki/Student%27s_t-distribution#Generalized_Student's_t-distribution).
Metadata
Owner
Metadata
Provides likelihood functions for Gaussian Processes.